© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26212
    Prev
    Next
    INDEX
    Explanations

    Island

    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
     nette
    -0.09
     delimiter
    -0.08
     UTF
    -0.08
     elective
    -0.08
    /banner
    -0.08
    Delimiter
    -0.08
    羽
    -0.08
     സ്ത്രീ
    -0.07
    Delimited
    -0.07
     羽
    -0.07
    POSITIVE LOGITS
    .schedule
    0.09
    .sleep
    0.08
     Kan
    0.08
    Scheduling
    0.08
     db
    0.08
     scheduling
    0.08
    .running
    0.08
    .pool
    0.07
    .actual
    0.07
    ತ್ತ
    0.07
    Activations Density 0.002%

    No Known Activations