© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95445
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ית
    -0.08
     предлагает
    -0.08
    dex
    -0.08
     abandoning
    -0.08
    ก
    -0.08
     مؤسسة
    -0.07
     anggota
    -0.07
     Qaeda
    -0.07
     cirugía
    -0.07
     medlem
    -0.07
    POSITIVE LOGITS
     overview
    0.14
     Overview
    0.11
     disclaim
    0.10
    概要
    0.09
     Conclusion
    0.09
     Disclaimer
    0.09
     summary
    0.09
    _summary
    0.09
     Summary
    0.09
     briefly
    0.09
    Activations Density 0.044%

    No Known Activations