© 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. 24736
    Prev
    Next
    INDEX
    Explanations

    走

    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
     Steak
    -0.08
     Joachim
    -0.08
    IATE
    -0.08
     Clara
    -0.08
     vér
    -0.08
     allant
    -0.08
     ون
    -0.07
    Dos
    -0.07
     EXACT
    -0.07
     FACT
    -0.07
    POSITIVE LOGITS
    完
    0.09
    ્યા
    0.08
    ્ટ
    0.07
    一步
    0.07
     đúng
    0.07
    ாவ
    0.07
    ковые
    0.07
    мер
    0.07
     multicultural
    0.07
     bann
    0.07
    Activations Density 0.003%

    No Known Activations