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

    Neuronpedia

    APICircuit 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. 12986
    Prev
    Next
    INDEX
    Explanations

    proper

    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
     computerized
    -0.08
     lại
    -0.08
    atório
    -0.07
    liwo
    -0.07
    नाक
    -0.07
    geta
    -0.07
    设施
    -0.07
     transc
    -0.07
    णा
    -0.07
    332
    -0.07
    POSITIVE LOGITS
     tambahan
    0.08
     Men
    0.08
     adicionales
    0.08
     Removed
    0.08
     Shelf
    0.08
     множ
    0.08
     Versions
    0.08
     humbled
    0.08
     способов
    0.08
     penis
    0.07
    Activations Density 0.004%

    No Known Activations