© 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. 68064
    Prev
    Next
    INDEX
    Explanations

    one-twelfth

    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
     kennen
    -0.08
     depart
    -0.08
     departure
    -0.08
     exited
    -0.08
     nutzen
    -0.08
     exit
    -0.07
     exits
    -0.07
     HQ
    -0.07
    .Zero
    -0.07
    HQ
    -0.07
    POSITIVE LOGITS
    二区
    0.09
     阜
    0.09
     φυ
    0.09
     окру
    0.08
    ויה
    0.08
    ρος
    0.08
     auxilia
    0.08
     adjacent
    0.08
    лама
    0.08
    очу
    0.08
    Activations Density 0.001%

    No Known Activations