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. 54181
    Prev
    Next
    INDEX
    Explanations

    polynomial remainder theorem

    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
    roles
    -0.09
     kayaking
    -0.08
    Extern
    -0.08
    _bundle
    -0.07
    Roles
    -0.07
    _threads
    -0.07
    nique
    -0.07
     rares
    -0.07
     blankets
    -0.07
    processed
    -0.07
    POSITIVE LOGITS
     Substitute
    0.09
     القي
    0.09
     remainder
    0.08
     substitution
    0.08
     sustit
    0.08
     rápidas
    0.08
     quick
    0.08
     Evaluate
    0.08
     substit
    0.08
    ошад
    0.08
    Activations Density 0.018%

    No Known Activations