© 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. 15-RESID-POST-AA
    11. 16359
    Prev
    Next
    INDEX
    Explanations

    say "equals"

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nip
    -0.08
    né
    -0.07
     Topic
    -0.07
     Norwegian
    -0.07
     ‘
    -0.07
     :)↵
    -0.07
     awal
    -0.07
     clicking
    -0.07
     🙂↵↵
    -0.07
     Nick
    -0.07
    POSITIVE LOGITS
     എന്നീ
    0.09
    ritur
    0.09
    .springboot
    0.09
    iteren
    0.09
    ienze
    0.09
    _RATIO
    0.08
    .viewer
    0.08
    lerden
    0.08
    .{
    0.08
     Сто
    0.08
    Activations Density 0.006%

    No Known Activations