© 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. 47266
    Prev
    Next
    INDEX
    Explanations

    array indexing in code

    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
     مك
    -0.08
    Compatible
    -0.08
    anden
    -0.07
    ాల్
    -0.07
     Dy
    -0.07
     loo
    -0.07
     faite
    -0.07
     aucun
    -0.07
    _cpp
    -0.07
    Era
    -0.07
    POSITIVE LOGITS
     Judas
    0.08
    陷
    0.08
     בעקבות
    0.08
    ूक
    0.08
     במקום
    0.08
     needless
    0.07
     twijf
    0.07
    wish
    0.07
     श्रद्ध
    0.07
    裏
    0.07
    Activations Density 0.003%

    No Known Activations