© 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. 91383
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    istically
    -0.08
     functioneren
    -0.08
    ────────
    -0.07
    ellipse
    -0.07
    	Description
    -0.07
    ────────────────
    -0.07
     시대
    -0.07
     nepot
    -0.07
    oused
    -0.07
     pathetic
    -0.07
    POSITIVE LOGITS
     recommande
    0.09
     arb
    0.09
     addicted
    0.08
     worldwide
    0.08
     аккаун
    0.08
     Vegan
    0.08
     rekomm
    0.08
     Ted
    0.08
     monetize
    0.08
     sushi
    0.08
    Activations Density 0.022%

    No Known Activations