© 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. 3-RESID-POST-AA
    11. 12861
    Prev
    Next
    INDEX
    Explanations

    共同

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     institut
    -0.08
    MI
    -0.08
    Gran
    -0.07
    gran
    -0.07
     мил
    -0.07
     JK
    -0.07
     피
    -0.07
    ln
    -0.07
     Christine
    -0.07
    Proced
    -0.07
    POSITIVE LOGITS
    isi
    0.08
     lieber
    0.08
     !(
    0.07
     ensures
    0.07
     Cheer
    0.07
     Cunningham
    0.07
     כך
    0.07
     Ci
    0.07
     imprint
    0.07
    一定
    0.07
    Activations Density 0.008%

    No Known Activations