© 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. 29047
    Prev
    Next
    INDEX
    Explanations

    recipes

    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
    生态
    -0.08
    多年
    -0.08
     annually
    -0.08
     Optimal
    -0.07
    胜
    -0.07
     acumul
    -0.07
    Doch
    -0.07
    रिया
    -0.07
    效率
    -0.07
     strugg
    -0.07
    POSITIVE LOGITS
     taza
    0.08
     tablespoon
    0.08
     dama
    0.08
    丁目
    0.08
     liters
    0.08
    Louis
    0.08
     بر
    0.08
    (""
    0.08
     teaspoon
    0.08
     لعب
    0.07
    Activations Density 0.008%

    No Known Activations