© 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. 65391
    Prev
    Next
    INDEX
    Explanations

    sea anemones and jellyfish

    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
     lk
    -0.08
     excellence
    -0.08
     loj
    -0.08
     econom
    -0.08
     ál
    -0.08
     समी
    -0.08
     Nür
    -0.08
     além
    -0.08
     yacc
    -0.08
     packaging
    -0.08
    POSITIVE LOGITS
    layer
    0.08
     violet
    0.08
     Vip
    0.08
    -layer
    0.08
     Danger
    0.08
     �
    0.08
    bee
    0.08
    fires
    0.08
     translucent
    0.08
    purple
    0.08
    Activations Density 0.003%

    No Known Activations