gpt-oss-20b-abliterated
20BGPT-OSS
from openai/gpt-oss-20b
↓ 32.8K♥ 22617 repos
gpt-oss-20b-heretic
gpt-oss-20b-heretic is a Heretic-ablated variant of openai/gpt-oss-20b, published on Hugging Face by p-e-w. It is 20B parameters, 24GB VRAM class class and apache-2.0 licence. It is distributed across 25 repositories in Transformers, GGUF and Full precision formats, totalling 6K downloads.
Specification
- Model name
- gpt-oss-20b-heretic
- Source repository
- p-e-w/gpt-oss-20b-heretic
- Base model
- openai/gpt-oss-20b
- Publisher
- p-e-w
- Parameters
- 20B
- VRAM required
- ~13 GB at Q4_K_M, 4k context (estimated) — runs on 16 GB cards
- Hardware class
- 10B – 25B — 24GB VRAM class
- Licence
- apache-2.0
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, Full precision
- First indexed
- 16 Nov 2025
- Last updated
- 16 Oct 2026
Ablation technique
How gpt-oss-20b-heretic was modified, and what that implies.
Heretic
Automated directional ablation via the Heretic toolchain, which searches for the refusal direction and applies it with a KL-divergence budget so general capability is preserved.
Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
From the publisher’s model card
“Welcome to the gpt-oss series, OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
Ollama (publisher-documented)
ollama run gpt-oss:20bllama.cpp / GGUF
hf download mradermacher/gpt-oss-20b-heretic-GGUF --local-dir ./gpt-oss-20b-heretic
llama-cli -m ./gpt-oss-20b-heretic/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "p-e-w/gpt-oss-20b-heretic"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve p-e-w/gpt-oss-20b-heretic --trust-remote-codeDownloads and variants (24)
Every published repository of gpt-oss-20b-heretic, including quantised re-releases by other authors.
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- gpt-oss-20b-heretic will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- Capability is inherited from openai/gpt-oss-20b, not added by ablation — at 20B parameters, expect roughly the base model’s competence, minus some instruction-following fidelity.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- Declared licence is apache-2.0, but the terms that bind you are openai/gpt-oss-20b’s — a re-release cannot grant more than its parent.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for gpt-oss-20b-heretic is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with p-e-w, and does not independently verify publisher claims. See responsible use.