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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 47786
    Prev
    Next
    INDEX
    Explanations

    as

    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
    હેર
    -0.09
     ચોક
    -0.08
     Hern
    -0.07
     Iterable
    -0.07
    iron
    -0.07
     ~$
    -0.07
     Yale
    -0.07
     tres
    -0.07
    Commons
    -0.07
    okuq
    -0.07
    POSITIVE LOGITS
     thereafter
    0.09
     النهاية
    0.09
     अंतिम
    0.09
    最后
    0.09
    最终
    0.09
     finalmente
    0.09
    最後
    0.09
     culmination
    0.09
     наконец
    0.09
     చివ
    0.09
    Activations Density 0.038%

    No Known Activations