© 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. 78374
    Prev
    Next
    INDEX
    Explanations

    Processes and actions

    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
    -0.08
     રહી
    -0.08
     тус
    -0.08
     либо
    -0.07
     toch
    -0.07
    ;/
    -0.07
    Terr
    -0.07
    Couldn't
    -0.07
    /↵/
    -0.07
     થઈ
    -0.07
    POSITIVE LOGITS
     וגם
    0.11
    itories
    0.07
     cả
    0.07
    ternational
    0.07
     सहित
    0.07
     עצמו
    0.07
     salga
    0.07
    ੍
    0.07
     DNI
    0.07
    igheter
    0.07
    Activations Density 0.258%
    No Known Activations