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. 111632
    Prev
    Next
    INDEX
    Explanations

    Equations and formulas

    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
    祭
    -0.08
     tam
    -0.08
    ơi
    -0.07
     boss
    -0.07
     pray
    -0.07
     shrine
    -0.07
     coping
    -0.07
     prayer
    -0.07
     shrub
    -0.07
    (torch
    -0.07
    POSITIVE LOGITS
     Jaz
    0.09
     NA
    0.08
     Ее
    0.08
     Alger
    0.08
    ION
    0.08
     mwan
    0.08
     נמ
    0.08
     Egyptian
    0.08
     नही
    0.08
     Lol
    0.08
    Activations Density 0.001%

    No Known Activations