© 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. 25892
    Prev
    Next
    INDEX
    Explanations

    of

    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
     हवा
    -0.07
    impan
    -0.07
     correctly
    -0.07
    .Normal
    -0.07
    lich
    -0.07
     accurately
    -0.07
     часы
    -0.07
    -to
    -0.07
     الدول
    -0.07
     первым
    -0.07
    POSITIVE LOGITS
     respective
    0.09
     unterschiedliche
    0.09
    不同
    0.09
     respectivamente
    0.09
     בעולם
    0.08
     각각
    0.08
     parehong
    0.08
     ವಿಭ
    0.08
    活動
    0.08
     într
    0.08
    Activations Density 0.062%

    No Known Activations