© 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. 99366
    Prev
    Next
    INDEX
    Explanations

    Christian

    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
     المالية
    -0.08
     liik
    -0.07
    hle
    -0.07
     جس
    -0.07
     Blick
    -0.07
     adjacent
    -0.07
    برز
    -0.07
    اج
    -0.07
     Lang
    -0.07
     Heng
    -0.07
    POSITIVE LOGITS
    izzare
    0.08
     centuries
    0.08
     Durant
    0.08
    elsius
    0.07
     persecution
    0.07
     comum
    0.07
     Somewhere
    0.07
     ವ
    0.07
     adipiscing
    0.07
    ಿಸ್ತ
    0.07
    Activations Density 0.011%

    No Known Activations