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. 19251
    Prev
    Next
    INDEX
    Explanations

    helped

    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
     خبره
    -0.08
     aceit
    -0.08
     عمد
    -0.08
    adzir
    -0.07
     fudge
    -0.07
     nhằm
    -0.07
     Соб
    -0.07
     repartir
    -0.07
     مگر
    -0.07
    udur
    -0.07
    POSITIVE LOGITS
     helped
    0.12
     sayesinde
    0.12
    Grâce
    0.12
    ありがとうございました
    0.11
     gracias
    0.11
     grazie
    0.10
     permitió
    0.10
     Grâce
    0.10
     gehol
    0.10
     플랫폼
    0.10
    Activations Density 0.152%

    No Known Activations