© 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. 23-RESID-POST-AA
    11. 47877
    Prev
    Next
    INDEX
    Explanations

    sqrt

    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
     Мат
    -0.09
     jenter
    -0.09
     {[
    -0.09
     അ
    -0.09
     بوك
    -0.09
     meninas
    -0.08
     Stade
    -0.08
     kadın
    -0.08
     Sabrina
    -0.08
     $('#
    -0.08
    POSITIVE LOGITS
    arm
    0.09
    hook
    0.08
    813
    0.08
    Root
    0.08
    root
    0.08
    Third
    0.08
    itre
    0.08
    eteer
    0.08
    prod
    0.08
    Tree
    0.08
    Activations Density 0.003%

    No Known Activations