© 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. 3-RESID-POST-AA
    11. 2574
    Prev
    Next
    INDEX
    Explanations

    ick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gross
    -0.08
     coord
    -0.08
     Nerv
    -0.08
     Kör
    -0.08
    kové
    -0.08
     Kristen
    -0.08
     pover
    -0.07
     typische
    -0.07
     pauvre
    -0.07
     Gj
    -0.07
    POSITIVE LOGITS
    Or
    0.08
    .timestamps
    0.08
    B
    0.08
    .SECONDS
    0.08
    Imp
    0.08
    USA
    0.07
    Of
    0.07
    ारा
    0.07
    .Resource
    0.07
     passion
    0.07
    Activations Density 0.000%

    No Known Activations