© 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. 103629
    Prev
    Next
    INDEX
    Explanations

    Proper names

    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
    /TR
    -0.10
    /ST
    -0.08
    /MM
    -0.08
     ($(
    -0.08
    /DD
    -0.08
     ($_
    -0.08
    /PT
    -0.08
     cms
    -0.08
    /u
    -0.07
     ${({
    -0.07
    POSITIVE LOGITS
     Kevin
    0.23
     Emily
    0.22
     Mike
    0.21
     Alex
    0.21
     Sarah
    0.21
     William
    0.21
     Chris
    0.21
     Peter
    0.21
     Mary's
    0.20
     Steve
    0.20
    Activations Density 1.010%

    No Known Activations