© 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. 68233
    Prev
    Next
    INDEX
    Explanations

    fell

    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
    commercial
    -0.08
     kron
    -0.08
    .naming
    -0.08
     discrepancy
    -0.07
     extension
    -0.07
    Extensions
    -0.07
     identifying
    -0.07
     verifica
    -0.07
    nero
    -0.07
    onyesha
    -0.07
    POSITIVE LOGITS
     Coke
    0.09
     %[
    0.08
     aboard
    0.08
     transports
    0.08
     Transporte
    0.08
     %+
    0.08
     dances
    0.08
    .Transport
    0.08
     casts
    0.08
     تامین
    0.08
    Activations Density 0.002%

    No Known Activations