© 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. 78809
    Prev
    Next
    INDEX
    Explanations

    tile

    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
     비
    -0.08
     tempfile
    -0.08
     동
    -0.08
    לית
    -0.08
    扑
    -0.07
     intern
    -0.07
     שמ
    -0.07
     House
    -0.07
    andishi
    -0.07
     Müll
    -0.07
    POSITIVE LOGITS
     оформление
    0.08
    ोजना
    0.07
    ριο
    0.07
    方案
    0.07
     bordered
    0.07
    ，包括
    0.07
     vergoeding
    0.07
     takeaway
    0.07
     inspired
    0.07
    روج
    0.07
    Activations Density 0.004%

    No Known Activations