© 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. 19-RESID-POST-AA
    11. 18417
    Prev
    Next
    INDEX
    Explanations

    say "br 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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     پذیر
    -0.09
     dago
    -0.08
     different
    -0.08
    <ID
    -0.08
    atically
    -0.08
     itself
    -0.08
     egiten
    -0.08
     پذ
    -0.08
     <=",
    -0.08
     <>",
    -0.08
    POSITIVE LOGITS
    %=
    0.20
    numerusform
    0.19
    ></
    0.18
    blockquote
    0.18
    div
    0.17
    span
    0.16
    script
    0.16
    br
    0.16
    textarea
    0.15
    >↵↵
    0.15
    Activations Density 0.052%

    No Known Activations