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. 15-RESID-POST-AA
    6. 150
    Prev
    Next
    INDEX
    Explanations

    age

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forderung
    -0.09
    aller
    -0.08
    ebab
    -0.08
     vouloir
    -0.08
     maatregelen
    -0.08
     gaussian
    -0.07
    eda
    -0.07
     humain
    -0.07
    <html
    -0.07
    まだ
    -0.07
    POSITIVE LOGITS
    Years
    0.16
     years
    0.15
     שנים
    0.15
     बित
    0.15
     वर्षों
    0.15
     tenure
    0.14
     jarenlang
    0.14
    years
    0.14
     yıll
    0.14
     годы
    0.13
    Activations Density 0.047%

    No Known Activations