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

    Neuronpedia

    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. 77853
    Prev
    Next
    INDEX
    Explanations

    .ui and extension

    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
     toplant
    -0.08
     Everyday
    -0.08
    യ
    -0.07
     East
    -0.07
     Chairman
    -0.07
     സമ്മേള
    -0.07
    ാഥ
    -0.07
     Chronic
    -0.07
    astas
    -0.07
    thon
    -0.07
    POSITIVE LOGITS
     surpass
    0.08
    ому
    0.07
     Beau
    0.07
     ern
    0.07
     marki
    0.07
     jur
    0.07
     supplemental
    0.07
     माँ
    0.07
    prog
    0.07
    िटी
    0.07
    Activations Density 0.000%

    No Known Activations