kabachuha/gpt-oss-20b-SOMbliterated
Abliterated vs openai/gpt-oss-20b. Looks like abliteration (refusal removal): only the output projections (o_proj) changed, in 22 of 24 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Norms 0/49, MLP 0/192, Attention 22/216, lm_head 0/1, Embeddings 0/1
3 derivatives checked
- mradermacher/gpt-oss-20b-SOMbliterated-i1-GGUF: Quantization
- mradermacher/gpt-oss-20b-SOMbliterated-GGUF: Quantization
- gghfez/gpt-oss-20b-SOMbliterated-mxfp4: Quantization