Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43782
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    MO
    -0.08
    SAL
    -0.08
    (Log
    -0.08
     kasa
    -0.08
    Ga
    -0.08
    Cash
    -0.08
     Augustus
    -0.08
     molts
    -0.08
    Wrap
    -0.07
     통한
    -0.07
    POSITIVE LOGITS
    ware
    0.09
     значения
    0.08
    项
    0.08
    块
    0.08
    事項
    0.08
    之
    0.08
    qd
    0.08
     രീത
    0.08
     पत्र
    0.08
     measure
    0.07
    Activations Density 0.432%

    No Known Activations