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. 19036
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     इसी
    -0.10
    ۔۔۔۔
    -0.10
     similarly
    -0.10
     somehow
    -0.10
     Yesu
    -0.10
     igualmente
    -0.10
     яго
    -0.10
     некоторые
    -0.10
     tambm
    -0.10
     რაღაც
    -0.10
    POSITIVE LOGITS
     :
    0.07
     emer
    0.07
     identifier
    0.06
     Multi
    0.06
    .invalidate
    0.06
    0.06
     if
    0.06
     인
    0.06
    ellectual
    0.06
     abbreviation
    0.06
    Activations Density 0.021%

    No Known Activations