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. 11941
    Prev
    Next
    INDEX
    Explanations

    long

    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
     judic
    -0.08
     semen
    -0.08
    artment
    -0.08
     계약
    -0.07
     re
    -0.07
     Jacob
    -0.07
     seasons
    -0.07
     капитал
    -0.07
    atom
    -0.07
    ogical
    -0.07
    POSITIVE LOGITS
    -duration
    0.11
     Longer
    0.10
     langere
    0.10
     largas
    0.10
     läng
    0.10
     (>
    0.10
     prolonged
    0.10
     endurance
    0.10
     longue
    0.10
     longer
    0.10
    Activations Density 0.010%

    No Known Activations