© 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. 8106
    Prev
    Next
    INDEX
    Explanations

    like

    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
     presumably
    -0.08
    /or
    -0.08
    veloper
    -0.07
     Bly
    -0.07
     griff
    -0.07
     irgende
    -0.07
    马上
    -0.07
    -lang
    -0.07
    었
    -0.07
    -là
    -0.07
    POSITIVE LOGITS
     saying
    0.09
     pren
    0.08
     discipline
    0.07
     ug
    0.07
    baix
    0.07
     المفت
    0.07
     teg
    0.07
     diciendo
    0.07
     guida
    0.07
     banget
    0.07
    Activations Density 0.013%

    No Known Activations