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. 55944
    Prev
    Next
    INDEX
    Explanations

    math ratios and fractions

    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
     ঘটে
    -0.08
    profiles
    -0.08
    同期
    -0.08
     تحقيق
    -0.08
     возникновения
    -0.08
    幻想
    -0.07
     ದು
    -0.07
     joiden
    -0.07
     ನಡೆದ
    -0.07
    狼人
    -0.07
    POSITIVE LOGITS
     표현
    0.11
     verbally
    0.10
     notation
    0.10
     phrase
    0.09
    Format
    0.09
     formats
    0.09
    表达
    0.09
     форме
    0.09
     convey
    0.09
     specify
    0.09
    Activations Density 0.086%

    No Known Activations