© 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. 95315
    Prev
    Next
    INDEX
    Explanations

    right

    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
    Mang
    -0.08
     Mang
    -0.08
    lí
    -0.07
    hips
    -0.07
    iren
    -0.07
    러
    -0.07
    echo
    -0.07
     Restr
    -0.07
     �
    -0.07
    já
    -0.07
    POSITIVE LOGITS
    -benar
    0.16
    正确
    0.12
     правиль
    0.12
     правильно
    0.11
     correcta
    0.10
     सही
    0.10
    _answers
    0.10
    Correct
    0.10
    대로
    0.09
     পথে
    0.09
    Activations Density 0.062%

    No Known Activations