© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 112606
    Prev
    Next
    INDEX
    Explanations

    spreadsheets, data analysis

    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
    Planet
    -0.08
    _HIGH
    -0.08
     communication
    -0.07
    .sh
    -0.07
    communication
    -0.07
    planet
    -0.07
    =true
    -0.07
     magazine
    -0.07
    _COMMENT
    -0.07
    Radio
    -0.07
    POSITIVE LOGITS
     Dollars
    0.09
     Emails
    0.09
    itivity
    0.09
     Área
    0.08
    セン
    0.08
     afikun
    0.08
     Townsend
    0.08
     ien
    0.08
     nsogbu
    0.08
    omme
    0.08
    Activations Density 0.002%

    No Known Activations