© 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. 64296
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
     느
    -0.07
     떨어
    -0.07
    �
    -0.07
    aler
    -0.07
     approximation
    -0.07
     pion
    -0.07
     propri
    -0.07
     Horm
    -0.07
     kari
    -0.07
     लगे
    -0.07
    POSITIVE LOGITS
     ஆகிய
    0.09
    istente
    0.08
    .Utc
    0.07
     slew
    0.07
     Tout
    0.07
    .Serialize
    0.07
    =result
    0.07
    Mas
    0.07
    Ws
    0.07
     timestamp
    0.07
    Activations Density 0.022%

    No Known Activations