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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 94989
    Prev
    Next
    INDEX
    Explanations

    definition

    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
     chants
    -0.07
    !.↵
    -0.07
    attered
    -0.07
    Lin
    -0.07
     nganti
    -0.07
    Sight
    -0.07
     {↵//↵//
    -0.07
     verkauft
    -0.07
    ierd
    -0.07
     있다는
    -0.07
    POSITIVE LOGITS
     bezeichnet
    0.08
     קצר
    0.08
     Gartner
    0.08
    φέ
    0.08
    hais
    0.08
     פל
    0.07
    erves
    0.07
    komb
    0.07
     Bildungs
    0.07
     Pare
    0.07
    Activations Density 0.030%

    No Known Activations