© 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. 78474
    Prev
    Next
    INDEX
    Explanations

    say

    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
    ecos
    -0.08
    yrus
    -0.07
     ba
    -0.07
     Quest
    -0.07
     boobs
    -0.07
    IRTUAL
    -0.07
    urbed
    -0.07
    ped
    -0.07
    -ba
    -0.07
    orage
    -0.07
    POSITIVE LOGITS
    0.08
    248
    0.08
     regarding
    0.08
    เพิ่มเติม
    0.08
     nuggets
    0.07
     releg
    0.07
    ю
    0.07
     메시
    0.07
     respecto
    0.07
     kertoo
    0.07
    Activations Density 0.012%
    No Known Activations