© 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. 95000
    Prev
    Next
    INDEX
    Explanations

    from

    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
     безопасность
    -0.08
     creativo
    -0.08
     creativity
    -0.08
     مدى
    -0.07
    entan
    -0.07
    -0.07
    -plus
    -0.07
    anth
    -0.07
     مقدم
    -0.07
     creative
    -0.07
    POSITIVE LOGITS
     countryside
    0.10
     Provence
    0.09
    籍
    0.09
     belakang
    0.08
     ग्रामीण
    0.08
     régions
    0.08
     Германии
    0.08
     rural
    0.08
     Bavaria
    0.08
     hometown
    0.08
    Activations Density 0.041%
    No Known Activations