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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 91272
    Prev
    Next
    INDEX
    Explanations

    Random text snippets

    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
    [obj
    -0.08
    .rules
    -0.07
    /gallery
    -0.07
     паў
    -0.07
     දෙ
    -0.07
     kalian
    -0.07
    [arg
    -0.07
     insults
    -0.07
     dupla
    -0.07
    .IOException
    -0.07
    POSITIVE LOGITS
    214
    0.08
    	top
    0.07
     presso
    0.07
    older
    0.07
     Wet
    0.07
     groot
    0.07
     verbose
    0.07
    (top
    0.07
     spinal
    0.07
    轩
    0.07
    Activations Density 11.859%

    No Known Activations