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

    Neuronpedia

    Jacobian LensNEW
    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. 63874
    Prev
    Next
    INDEX
    Explanations

    Rolling dough

    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
     מזה
    -0.08
    '][
    -0.08
     supplemental
    -0.08
    Supplement
    -0.08
    delivr
    -0.08
     Supplemental
    -0.08
     accompanied
    -0.07
    ']]['
    -0.07
    death
    -0.07
     sier
    -0.07
    POSITIVE LOGITS
     occurrences
    0.09
    .find
    0.09
    ophageal
    0.08
    	find
    0.08
    /find
    0.08
     strstr
    0.08
     strpos
    0.08
    _FIND
    0.08
    clusions
    0.08
    穿
    0.08
    Activations Density 0.025%

    No Known Activations