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. 77414
    Prev
    Next
    INDEX
    Explanations

    database, files, sheets code snippets

    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
     �
    -0.08
    (strategy
    -0.08
     Wealth
    -0.07
    (name
    -0.07
     conveying
    -0.07
    .variant
    -0.07
     porto
    -0.07
     Intelig
    -0.07
     intelig
    -0.07
     Vertrieb
    -0.07
    POSITIVE LOGITS
     Sib
    0.08
     tubing
    0.08
    tolist
    0.08
     tad
    0.08
    compressed
    0.08
     BPM
    0.07
     chast
    0.07
    -reading
    0.07
    dbh
    0.07
    ominator
    0.07
    Activations Density 0.001%

    No Known Activations