© 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. 94807
    Prev
    Next
    INDEX
    Explanations

    Chinese characters 尽/敬

    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
    (sol
    -0.08
    ettes
    -0.08
     Félix
    -0.08
    oney
    -0.07
     OZ
    -0.07
     vr
    -0.07
     traduc
    -0.07
    ilities
    -0.07
    elingen
    -0.07
    ng
    -0.07
    POSITIVE LOGITS
    èn
    0.07
     हाल
    0.07
    ън
    0.07
    0.07
    0.07
     Jem
    0.07
     slowing
    0.07
     назар
    0.07
    ৰ
    0.07
     qoy
    0.06
    Activations Density 0.007%
    No Known Activations