Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90158
    Prev
    Next
    INDEX
    Explanations

    quick-witted personality traits

    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
    egen
    -0.09
     sucks
    -0.08
     unders
    -0.08
    prote
    -0.08
    [S
    -0.08
     desc
    -0.08
     Butler
    -0.08
     Electoral
    -0.07
    documents
    -0.07
     Constitu
    -0.07
    POSITIVE LOGITS
     agility
    0.11
     ઝડપી
    0.11
    刀
    0.09
     స్పంద
    0.09
     الحركة
    0.09
     زړه
    0.09
     agile
    0.09
     العقل
    0.09
     siab
    0.09
     عقل
    0.09
    Activations Density 0.006%

    No Known Activations