© 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. 729
    Prev
    Next
    INDEX
    Explanations

    transition words

    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
     interpreted
    -0.08
     itiner
    -0.07
     interpre
    -0.07
    161
    -0.07
    niers
    -0.07
     interpr
    -0.07
    多人
    -0.07
     пут
    -0.07
    -0.07
     chopped
    -0.07
    POSITIVE LOGITS
     verloop
    0.09
     Improving
    0.09
     progressing
    0.09
    siwaju
    0.09
     overgang
    0.08
     Lorem
    0.08
     connector
    0.08
     aiding
    0.08
    .BOTTOM
    0.08
    երջ
    0.08
    Activations Density 0.003%
    No Known Activations