Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98671
    Prev
    Next
    INDEX
    Explanations

    س

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    šanās
    -0.08
     ROI
    -0.08
    ROI
    -0.08
    тая
    -0.08
    ્ત
    -0.07
    worksheet
    -0.07
     thous
    -0.07
     મુખ્ય
    -0.07
     Loyola
    -0.07
     exempt
    -0.07
    POSITIVE LOGITS
    لسل
    0.09
    ارع
    0.09
    (time
    0.08
    	time
    0.08
     time
    0.08
    ائل
    0.08
    례
    0.08
    /compiler
    0.07
    ارب
    0.07
    لق
    0.07
    Activations Density 0.000%

    No Known Activations