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. 54052
    Prev
    Next
    INDEX
    Explanations

    Souls

    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
     justified
    -0.09
     היום
    -0.08
     கொண்ட
    -0.08
     اليوم
    -0.08
     DNS
    -0.07
     CDN
    -0.07
    stav
    -0.07
     עכשיו
    -0.07
    ocon
    -0.07
     நே
    -0.07
    POSITIVE LOGITS
     ки
    0.08
    Position
    0.07
    Starter
    0.07
    Esta
    0.07
    Snippet
    0.07
    Retry
    0.07
    Elite
    0.07
    Goto
    0.07
    iscard
    0.07
     Basement
    0.07
    Activations Density 0.003%

    No Known Activations