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. 98125
    Prev
    Next
    INDEX
    Explanations

    Possibly non-English text

    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
     ʻana
    -0.10
    issement
    -0.09
    вав
    -0.09
    adora
    -0.08
    izarea
    -0.08
    ÇÃO
    -0.08
     beinh
    -0.08
    atching
    -0.07
    cing
    -0.07
    едлив
    -0.07
    POSITIVE LOGITS
    ированы
    0.21
    альны
    0.20
    альна
    0.20
     आहे
    0.19
     છે
    0.19
    ирована
    0.19
    മാണ്
    0.19
    ವಾಗಿದೆ
    0.19
    ировано
    0.18
    ованы
    0.17
    Activations Density 0.056%

    No Known Activations