© 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. 99289
    Prev
    Next
    INDEX
    Explanations

    Code and styling

    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
     расс
    -0.09
     Spiral
    -0.07
    వర
    -0.07
    -0.07
     Crane
    -0.07
     spiral
    -0.07
     revista
    -0.07
    hok
    -0.07
    rama
    -0.07
     daerah
    -0.07
    POSITIVE LOGITS
    777
    0.08
     bigint
    0.08
    .CSS
    0.08
     */,↵
    0.07
     ala
    0.07
     GETGLOBAL
    0.07
    _grade
    0.07
    �
    0.07
    anje
    0.07
    /javascript
    0.07
    Activations Density 0.003%
    No Known Activations