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. 15-RESID-POST-AA
    6. 19160
    Prev
    Next
    INDEX
    Explanations

    parallel

    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
     different
    -0.07
    Different
    -0.07
     preprocess
    -0.07
    Combine
    -0.07
    这是
    -0.07
    Party
    -0.07
     combine
    -0.07
    'i
    -0.07
     periodically
    -0.07
     problema
    -0.07
    POSITIVE LOGITS
     للر
    0.09
     Salut
    0.08
     لـ
    0.08
     promoção
    0.08
     longe
    0.08
    /no
    0.08
     Xar
    0.08
     Município
    0.08
     Ohne
    0.08
    ”、
    0.08
    Activations Density 0.006%

    No Known Activations