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. 98549
    Prev
    Next
    INDEX
    Explanations

    of

    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
     types
    -0.09
     somehow
    -0.09
     etc
    -0.08
    -types
    -0.08
     Types
    -0.08
     Somehow
    -0.08
     type
    -0.08
    一定
    -0.08
    -type
    -0.08
     מסוג
    -0.08
    POSITIVE LOGITS
    gelijke
    0.19
     деятельности
    0.16
     діяль
    0.15
     działal
    0.14
     жилья
    0.12
     спорта
    0.12
     топлива
    0.12
     dienstverlening
    0.11
     cuisine
    0.11
     поведения
    0.11
    Activations Density 0.048%

    No Known Activations