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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98642
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     majorité
    -0.10
     Matching
    -0.09
     Winning
    -0.09
     Different
    -0.08
     schneller
    -0.08
     Smaller
    -0.08
    Matching
    -0.08
     Reduction
    -0.08
     Majority
    -0.08
     Breaking
    -0.08
    POSITIVE LOGITS
     taken
    0.16
     raised
    0.15
     all
    0.15
     inserted
    0.15
     evaluated
    0.14
     summed
    0.14
     plugged
    0.14
     operated
    0.14
     elevated
    0.13
     acted
    0.13
    Activations Density 0.137%

    No Known Activations