© 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. 50450
    Prev
    Next
    INDEX
    Explanations

    Math answers and explanations

    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
    999
    -0.10
    ,..
    -0.09
    stuff
    -0.09
    .id
    -0.09
    /...
    -0.09
    IA
    -0.09
    ame
    -0.09
    yg
    -0.09
    start
    -0.08
    500
    -0.08
    POSITIVE LOGITS
     $\
    0.25
     \
    0.21
     \(
    0.20
     【
    0.18
     **
    0.18
     `$
    0.18
     \<
    0.17
     "\
    0.17
     \$
    0.17
     Approximately
    0.17
    Activations Density 0.188%

    No Known Activations