© 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. 47824
    Prev
    Next
    INDEX
    Explanations

    wanting

    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
    島
    -0.09
     бывают
    -0.08
     എന്ന
    -0.08
    ਠ
    -0.08
     rebuilding
    -0.08
    ア
    -0.07
     суш
    -0.07
    letion
    -0.07
    eree
    -0.07
    という
    -0.07
    POSITIVE LOGITS
    Wanted
    0.10
     sought
    0.08
     minute
    0.08
     elusive
    0.08
     antid
    0.07
    Quantity
    0.07
     desej
    0.07
    หา
    0.07
    Body
    0.07
     undes
    0.07
    Activations Density 0.019%

    No Known Activations