© 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. 91351
    Prev
    Next
    INDEX
    Explanations

    routes

    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
     меч
    -0.07
     разобраться
    -0.07
     choosing
    -0.07
     aas
    -0.07
     ag
    -0.07
     omstandigheden
    -0.07
    _constructor
    -0.07
     обстоятель
    -0.07
     болезни
    -0.07
     Cassidy
    -0.07
    POSITIVE LOGITS
    fól
    0.08
     Ums
    0.08
    _cmos
    0.08
     vuur
    0.08
     entrusted
    0.08
    orium
    0.08
    人口
    0.08
     لوحة
    0.08
     grouped
    0.07
    ured
    0.07
    Activations Density 0.000%

    No Known Activations