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. 15-RESID-POST-AA
    6. 36
    Prev
    Next
    INDEX
    Explanations

    math problem analysis

    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
     boosts
    -0.07
     layers
    -0.07
     ss
    -0.07
     зоны
    -0.07
    /n
    -0.07
     turbulent
    -0.07
    /Documents
    -0.07
    -gu
    -0.07
     Kilometer
    -0.07
     Nürnberg
    -0.07
    POSITIVE LOGITS
    hebbers
    0.09
    مبر
    0.09
    your
    0.09
    ardu
    0.09
    ây
    0.09
    破解
    0.08
     ↵↵
    0.08
     jadx
    0.08
     आपके
    0.08
    ամբ
    0.08
    Activations Density 0.037%

    No Known Activations