Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 11991
    Prev
    Next
    INDEX
    Explanations

    tossing/rolling

    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
    Proto
    -0.08
     jemand
    -0.08
    prototype
    -0.08
    project
    -0.07
    _proto
    -0.07
     virtue
    -0.07
     gon
    -0.07
    green
    -0.07
    embed
    -0.07
    endor
    -0.07
    POSITIVE LOGITS
     repeatedly
    0.16
     consecut
    0.16
     successive
    0.14
    次数
    0.14
     consecutive
    0.14
    连续
    0.13
     sequential
    0.13
    不断
    0.12
     repeated
    0.12
     подряд
    0.12
    Activations Density 0.038%

    No Known Activations