© 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. 99256
    Prev
    Next
    INDEX
    Explanations

    stargazing

    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
     adher
    -0.08
     adhere
    -0.08
     repeats
    -0.07
     graphic
    -0.07
     appearances
    -0.07
     graphical
    -0.07
     appearance
    -0.07
     impre
    -0.07
    ено
    -0.07
    cate
    -0.07
    POSITIVE LOGITS
    بت
    0.08
    miércoles
    0.08
     fitter
    0.08
     fried
    0.08
     arsen
    0.08
     لديها
    0.08
    Charlie
    0.08
     poisoned
    0.08
    姐
    0.08
     quitter
    0.08
    Activations Density 0.002%

    No Known Activations