© 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. 44596
    Prev
    Next
    INDEX
    Explanations

    delegate

    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
    .socket
    -0.07
     Slam
    -0.07
    583
    -0.07
    (Byte
    -0.07
     pung
    -0.07
    �വ
    -0.07
     হল
    -0.07
    Cube
    -0.07
     lat
    -0.07
     בישראל
    -0.07
    POSITIVE LOGITS
     трен
    0.09
    -Pierre
    0.08
    ़
    0.08
     Ni
    0.08
    ોખ
    0.08
     autón
    0.07
    Ni
    0.07
     Müller
    0.07
     TRAIN
    0.07
    -as
    0.07
    Activations Density 0.000%

    No Known Activations