© 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. 24786
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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
     difficult
    -0.08
     bast
    -0.08
     angel
    -0.08
     بحث
    -0.08
     oefenen
    -0.08
     recent
    -0.07
     sting
    -0.07
     sneaker
    -0.07
     ●
    -0.07
     num
    -0.07
    POSITIVE LOGITS
     Cave
    0.08
     Verl
    0.08
     Converse
    0.08
     Wonders
    0.08
    quí
    0.07
    assuming
    0.07
    /sites
    0.07
     irrespective
    0.07
     gratuits
    0.07
    ('/:
    0.07
    Activations Density 0.099%

    No Known Activations