© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30464
    Prev
    Next
    INDEX
    Explanations

    am

    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
    Trump
    -0.08
    Amanda
    -0.08
    Merc
    -0.08
    Zimbabwe
    -0.08
    hier
    -0.08
                         ↵
    -0.08
     رد
    -0.08
    qualified
    -0.08
    flakes
    -0.07
     Trump
    -0.07
    POSITIVE LOGITS
     Algebra
    0.09
     algebra
    0.09
     Serialized
    0.08
    (adj
    0.08
     arithmetic
    0.08
    աք
    0.08
     ари
    0.07
    江
    0.07
     anyị
    0.07
    .Immutable
    0.07
    Activations Density 0.007%

    No Known Activations