Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65676
    Prev
    Next
    INDEX
    Explanations

    om

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quartet
    -0.08
     Largo
    -0.08
     Verk
    -0.08
     déc
    -0.08
    Pi
    -0.08
     phyt
    -0.07
     обо
    -0.07
     dette
    -0.07
     Quartet
    -0.07
     гра
    -0.07
    POSITIVE LOGITS
    เงิน
    0.08
     polic
    0.08
    []{
    0.07
     dys
    0.07
    296
    0.07
     Boden
    0.07
     stiff
    0.07
     다
    0.07
     ...)
    0.07
    styl
    0.07
    Activations Density 0.004%

    No Known Activations