© 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. 44924
    Prev
    Next
    INDEX
    Explanations

    use

    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
     जिसने
    -0.09
     خيار
    -0.08
     ktoś
    -0.08
     parmi
    -0.08
     વિક
    -0.07
     प्राकृतिक
    -0.07
     mutum
    -0.07
     aquellas
    -0.07
     changer
    -0.07
    atero
    -0.07
    POSITIVE LOGITS
     heavily
    0.09
    unused
    0.08
    .used
    0.08
     ниг
    0.08
    Unused
    0.08
     основном
    0.08
    jade
    0.08
     benötigen
    0.08
     голову
    0.08
    PI
    0.08
    Activations Density 0.030%

    No Known Activations