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. 112942
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas/equations

    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
    ю
    -0.08
     hum
    -0.08
    Inspection
    -0.07
     bgcolor
    -0.07
     sei
    -0.07
    Fault
    -0.07
    ตั้ง
    -0.07
     точно
    -0.07
    awat
    -0.07
    维修
    -0.07
    POSITIVE LOGITS
     logits
    0.15
    _logits
    0.10
    .softmax
    0.09
    relu
    0.09
     sharpen
    0.08
     exponent
    0.08
     palace
    0.08
     لعب
    0.08
     caches
    0.08
    ranking
    0.08
    Activations Density 0.002%

    No Known Activations