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. 11-RESID-POST-AA
    6. 54028
    Prev
    Next
    INDEX
    Explanations

    statistical variance

    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
     greet
    -0.08
     barter
    -0.08
     제작
    -0.08
     Rescue
    -0.08
     chees
    -0.08
     collectibles
    -0.08
     dinner
    -0.08
     landing
    -0.08
     traffic
    -0.08
    .reverse
    -0.08
    POSITIVE LOGITS
     covariance
    0.12
    Variance
    0.11
    Entropy
    0.10
    σ
    0.10
     variance
    0.10
    variance
    0.10
     σ
    0.10
    stderr
    0.10
     Shannon
    0.10
    _entropy
    0.10
    Activations Density 0.025%

    No Known Activations