© 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. 78822
    Prev
    Next
    INDEX
    Explanations

    midpoints

    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
     address
    -0.08
    ")]↵
    -0.08
     destination
    -0.07
     disability
    -0.07
     pathology
    -0.07
     democrat
    -0.07
    <java
    -0.07
    strike
    -0.07
    ajaj
    -0.07
     pato
    -0.07
    POSITIVE LOGITS
    .gu
    0.08
    oung
    0.08
    矩
    0.08
     triun
    0.08
    inflate
    0.08
    Mongo
    0.08
     Brooks
    0.08
    -gu
    0.07
     reportedly
    0.07
    /framework
    0.07
    Activations Density 0.009%

    No Known Activations