© 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. 45221
    Prev
    Next
    INDEX
    Explanations

    Code editor shortcuts

    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
     appréc
    -0.09
     appartement
    -0.08
    がお
    -0.08
     households
    -0.08
     नम
    -0.08
    _axes
    -0.07
     habit
    -0.07
     household
    -0.07
     impér
    -0.07
     senhora
    -0.07
    POSITIVE LOGITS
     Lookup
    0.09
    @Named
    0.09
    Lookup
    0.09
    Expandable
    0.08
     stare
    0.08
    peek
    0.08
     lookup
    0.08
    Oracle
    0.08
    pawn
    0.08
    Occurrences
    0.08
    Activations Density 0.003%

    No Known Activations