© 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. 23-RESID-POST-AA
    11. 51763
    Prev
    Next
    INDEX
    Explanations

    Currency and Russian symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gn
    -0.07
    Gj
    -0.07
    सब
    -0.07
    Ki
    -0.07
    izə
    -0.07
     fordert
    -0.07
     gateway
    -0.07
     incoming
    -0.07
     COMM
    -0.07
    ικής
    -0.07
    POSITIVE LOGITS
    /us
    0.10
    assle
    0.08
     Winkel
    0.08
     punts
    0.07
    elescope
    0.07
     doul
    0.07
     دینے
    0.07
     Ape
    0.07
    ющий
    0.07
    рол
    0.07
    Activations Density 0.000%

    No Known Activations