© 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. 5551
    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
     sqrt
    -0.09
     ورځ
    -0.09
    afruit
    -0.09
     ايم
    -0.09
     velen
    -0.08
     bigint
    -0.08
     deň
    -0.08
     necesidad
    -0.08
     necessitat
    -0.08
     avui
    -0.08
    POSITIVE LOGITS
    {
    0.10
    []{
    0.09
    {k
    0.08
    [K
    0.07
    [a
    0.07
    личес
    0.07
    13
    0.07
    {/*
    0.07
    {|
    0.07
    LOS
    0.07
    Activations Density 0.044%

    No Known Activations