© 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 EvalsExportsinterp-engineNEWAPI 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. 111464
    Prev
    Next
    INDEX
    Explanations

    timeline

    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
     tún
    -0.08
     Twilight
    -0.07
    養
    -0.07
     knob
    -0.07
     chops
    -0.07
    قر
    -0.07
    rs
    -0.07
     zen
    -0.07
     Council
    -0.07
     நோ
    -0.07
    POSITIVE LOGITS
    /calendar
    0.08
    ograma
    0.08
    (calendar
    0.08
    payments
    0.07
    ogram
    0.07
    �
    0.07
     prag
    0.07
    .calendar
    0.07
    Доп
    0.07
    (月
    0.07
    Activations Density 0.005%

    No Known Activations