© 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. 68278
    Prev
    Next
    INDEX
    Explanations

    parsing list of integers

    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
     moviment
    -0.08
     topped
    -0.08
     exer
    -0.08
     maatschappelijke
    -0.08
    Daddy
    -0.08
     घूम
    -0.08
    471
    -0.08
    Mounted
    -0.07
    veloped
    -0.07
    ancellable
    -0.07
    POSITIVE LOGITS
     Parse
    0.10
     parsed
    0.10
     parse
    0.10
     parsing
    0.10
    	parse
    0.09
     commas
    0.09
    .parse
    0.09
    =parse
    0.09
     Parsing
    0.09
    _parse
    0.09
    Activations Density 0.013%

    No Known Activations