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. 130915
    Prev
    Next
    INDEX
    Explanations

    commas

    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
     целью
    -0.08
     可
    -0.08
    اري
    -0.08
     zur
    -0.08
     parha
    -0.08
    oric
    -0.08
    angian
    -0.08
     necə
    -0.07
     كيفية
    -0.07
     温
    -0.07
    POSITIVE LOGITS
     чтобы
    0.20
     щоб
    0.19
     որպեսզի
    0.15
     aby
    0.15
    ч
    0.15
     যাতে
    0.14
     чтоб
    0.13
     որ
    0.13
     каб
    0.13
    ให้
    0.12
    Activations Density 0.012%

    No Known Activations