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. 106337
    Prev
    Next
    INDEX
    Explanations

    Swap

    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
     Rücken
    -0.09
     Sarah
    -0.09
     Hoover
    -0.08
     reconstructed
    -0.08
     Mari
    -0.08
    Sarah
    -0.08
     مسلسل
    -0.08
    icur
    -0.08
    Lisa
    -0.08
     copii
    -0.08
    POSITIVE LOGITS
    Trip
    0.08
    ENUM
    0.08
    Print
    0.07
    chaus
    0.07
    isen
    0.07
    (argc
    0.07
     volatile
    0.07
    0.07
    volatile
    0.07
    XPath
    0.07
    Activations Density 0.000%

    No Known Activations