© 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. 45698
    Prev
    Next
    INDEX
    Explanations

    cpu

    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
     Dar
    -0.07
    Exists
    -0.07
     Daniels
    -0.07
    Suc
    -0.07
    mlin
    -0.07
     mola
    -0.07
    icles
    -0.07
     校
    -0.07
    .has
    -0.07
     spring
    -0.07
    POSITIVE LOGITS
     হাতে
    0.08
     unbear
    0.08
     اقتصاد
    0.08
    -side
    0.08
     painfully
    0.07
     Dez
    0.07
     responsáveis
    0.07
    ოლო
    0.07
    担当
    0.07
    財布
    0.07
    Activations Density 0.003%

    No Known Activations