© 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. 7-RESID-POST-AA
    11. 1263
    Prev
    Next
    INDEX
    Explanations

    content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.09
    про
    -0.08
     emotion
    -0.07
     Survivor
    -0.07
    -bind
    -0.07
     marcador
    -0.07
     Girl
    -0.07
     serialization
    -0.07
     sanitized
    -0.07
     intent
    -0.07
    POSITIVE LOGITS
     zufrieden
    0.09
     flatter
    0.08
    ijt
    0.08
    Lng
    0.08
    arro
    0.08
     satisfactor
    0.08
     plateau
    0.08
     Tol
    0.08
     satisfactory
    0.08
     Eaton
    0.08
    Activations Density 0.023%
    No Known Activations