Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 54033
    Prev
    Next
    INDEX
    Explanations

    ism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mọ
    -0.07
    特点
    -0.07
     combinación
    -0.07
     Trie
    -0.07
    ��
    -0.07
    ¼
    -0.07
     Birch
    -0.07
     maintenant
    -0.07
     pelea
    -0.07
     ubicación
    -0.07
    POSITIVE LOGITS
    dern
    0.09
     distracted
    0.08
    veloper
    0.07
    \v
    0.07
    /views
    0.07
     ഫെ
    0.07
    拿
    0.07
     отзыв
    0.07
    指出
    0.07
     punctual
    0.07
    Activations Density 0.000%

    No Known Activations