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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 129759
    Prev
    Next
    INDEX
    Explanations

    Math problems with A, B

    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
     atlas
    -0.08
    েদন
    -0.08
     در
    -0.07
     Celsius
    -0.07
    .ly
    -0.07
     ola
    -0.07
     //_
    -0.07
    cea
    -0.07
     sols
    -0.07
    atlas
    -0.07
    POSITIVE LOGITS
    에게
    0.08
    先生
    0.08
    -san
    0.08
    那里
    0.08
     ten
    0.08
     engr
    0.08
    ’S
    0.08
    тің
    0.08
     Ten
    0.08
     Yem
    0.08
    Activations Density 0.064%

    No Known Activations