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. 19326
    Prev
    Next
    INDEX
    Explanations

    Like

    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
     Habitat
    -0.07
     zoo
    -0.07
     precipitation
    -0.07
     flora
    -0.07
     matéria
    -0.07
    ituation
    -0.07
     Sheila
    -0.07
     Teknik
    -0.07
     Matter
    -0.07
    Middleware
    -0.07
    POSITIVE LOGITS
     👍
    0.11
     dacă
    0.09
     hesitate
    0.09
    按钮
    0.08
     rewarded
    0.08
    页面
    0.08
     страницу
    0.08
     russ
    0.08
    👍
    0.08
     tombol
    0.08
    Activations Density 0.002%

    No Known Activations