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. 88190
    Prev
    Next
    INDEX
    Explanations

    organelles

    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
     вер
    -0.08
     sext
    -0.08
    顶
    -0.07
     λ
    -0.07
     kamera
    -0.07
     curated
    -0.07
    atég
    -0.07
     উদ্যোগ
    -0.07
    Hak
    -0.07
    Mart
    -0.07
    POSITIVE LOGITS
     apoptosis
    0.10
     gift
    0.08
     powerhouse
    0.08
     consent
    0.07
    raag
    0.07
     kemi
    0.07
     thighs
    0.07
     قلب
    0.07
     island
    0.07
    gift
    0.07
    Activations Density 0.001%

    No Known Activations