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. 15-RESID-POST-AA
    6. 19039
    Prev
    Next
    INDEX
    Explanations

    Comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     જાણવા
    -0.09
     അറിയ
    -0.08
     സമ്മേള
    -0.08
     vagu
    -0.08
     കൂടി
    -0.08
    ിനിമ
    -0.07
     പ്ര
    -0.07
     Fram
    -0.07
     സംഗ
    -0.07
     continues
    -0.07
    POSITIVE LOGITS
    ores
    0.09
    gravity
    0.08
    roid
    0.08
    Ã
    0.08
    eta
    0.08
    },{
    0.08
    heat
    0.08
    grades
    0.08
    }{
    0.08
    â
    0.08
    Activations Density 0.012%

    No Known Activations