© 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. 75473
    Prev
    Next
    INDEX
    Explanations

    微博

    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
     artes
    -0.08
    .executor
    -0.08
     Finger
    -0.08
     selet
    -0.08
     الحق
    -0.08
    ámara
    -0.08
    -handed
    -0.08
    재
    -0.08
     Hampton
    -0.07
    经理
    -0.07
    POSITIVE LOGITS
     cosplay
    0.09
     Eurovision
    0.09
     redd
    0.08
    Burn
    0.08
     addon
    0.08
    VOL
    0.08
     mosaic
    0.08
    irls
    0.07
     facilities
    0.07
     Dodge
    0.07
    Activations Density 0.004%

    No Known Activations