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. 98098
    Prev
    Next
    INDEX
    Explanations

    the

    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
     use
    -0.13
     χρήση
    -0.12
     notion
    -0.12
     của
    -0.11
     gebruik
    -0.11
     ανάγκ
    -0.11
     details
    -0.10
     focus
    -0.10
     définition
    -0.10
     uso
    -0.10
    POSITIVE LOGITS
     Jahrhunderts
    0.14
     century
    0.13
     Century
    0.13
     Month
    0.13
     ושל
    0.12
     damned
    0.12
     siècle
    0.12
     universe
    0.12
     gods
    0.12
     Woche
    0.12
    Activations Density 0.052%

    No Known Activations