© 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. 95061
    Prev
    Next
    INDEX
    Explanations

    charcoal

    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
     Serialize
    -0.08
     paying
    -0.08
    Yaml
    -0.07
    grpc
    -0.07
    ungi
    -0.07
     quinoa
    -0.07
     Paying
    -0.07
     yaml
    -0.07
    ationship
    -0.07
     ministries
    -0.07
    POSITIVE LOGITS
    笔
    0.09
    描
    0.09
    筆
    0.09
    午後
    0.08
     sightings
    0.08
    (stmt
    0.08
     कलाकार
    0.08
     लगाया
    0.08
     panne
    0.08
     инструмент
    0.08
    Activations Density 0.003%

    No Known Activations