© 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. 54777
    Prev
    Next
    INDEX
    Explanations

    Russian

    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
     orin
    -0.09
    .jar
    -0.09
     tides
    -0.08
     छल
    -0.08
    :path
    -0.08
     hord
    -0.08
     leaps
    -0.08
     Gwyn
    -0.07
     Phantom
    -0.07
    arada
    -0.07
    POSITIVE LOGITS
    Convert
    0.08
     Convert
    0.08
     বেশ
    0.08
     Tradu
    0.08
    Mi
    0.07
     Requested
    0.07
     quieren
    0.07
     україн
    0.07
    Complaint
    0.07
     
    0.07
    Activations Density 0.017%

    No Known Activations