© 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. 51787
    Prev
    Next
    INDEX
    Explanations

    say beginning of word

    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
     practical
    -0.08
     graph
    -0.08
    빠
    -0.07
    ’를
    -0.07
     kernel
    -0.07
     kinetic
    -0.07
     h
    -0.07
    ”
    -0.07
     disappearance
    -0.07
     und
    -0.07
    POSITIVE LOGITS
     returndata
    0.09
     tantr
    0.09
    ома
    0.09
     rechazo
    0.08
    ADING
    0.08
    ıyorum
    0.08
     desktops
    0.08
     boca
    0.08
    한다고
    0.08
    했다고
    0.08
    Activations Density 0.000%

    No Known Activations