© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1485
    Prev
    Next
    INDEX
    Explanations

    ln

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Senegal
    -0.08
    øre
    -0.08
     Ans
    -0.08
     killed
    -0.08
     أحدث
    -0.08
     appears
    -0.08
     painel
    -0.07
     tenor
    -0.07
     dez
    -0.07
    иши
    -0.07
    POSITIVE LOGITS
     exquis
    0.07
    ાર્થી
    0.07
     courting
    0.07
     enhancer
    0.07
    �
    0.07
    培
    0.07
     cortic
    0.07
    ajos
    0.07
    ယူ
    0.07
    cepts
    0.07
    Activations Density 0.017%

    No Known Activations