© 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. 1047
    Prev
    Next
    INDEX
    Explanations

    method

    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
    াইজ
    -0.08
    িঠ
    -0.08
    াকা
    -0.08
    -most
    -0.08
     صد
    -0.08
    ボ
    -0.07
     güçlü
    -0.07
    钟
    -0.07
    (vol
    -0.07
     Waffen
    -0.07
    POSITIVE LOGITS
     scand
    0.10
    पत्र
    0.09
     क्र
    0.08
    ете
    0.08
     thankful
    0.07
     reck
    0.07
    .misc
    0.07
     krok
    0.07
     privacidad
    0.07
     Reck
    0.07
    Activations Density 0.003%

    No Known Activations