© 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. 19-RESID-POST-AA
    11. 102403
    Prev
    Next
    INDEX
    Explanations

    parenthesis

    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
     <↵
    -0.10
     %",↵
    -0.10
     ?>"↵
    -0.09
     $↵
    -0.09
    ，↵
    -0.09
     €↵
    -0.09
     comprobar
    -0.09
    zenten
    -0.09
     ehkä
    -0.09
     addedge
    -0.08
    POSITIVE LOGITS
    `
    0.17
    (and
    0.17
    ``
    0.17
    (s
    0.16
    (e
    0.16
    (the
    0.16
    (in
    0.16
    (
    0.15
    (S
    0.15
    (with
    0.15
    Activations Density 0.008%

    No Known Activations