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. 111865
    Prev
    Next
    INDEX
    Explanations

    shared memory code snippets

    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
     пики
    -0.09
     취
    -0.09
    pendency
    -0.09
     microscopy
    -0.08
     নিউজ
    -0.08
     न्यूज
    -0.08
     blog
    -0.08
     vitaminas
    -0.08
    Newsletter
    -0.08
     biking
    -0.08
    POSITIVE LOGITS
    (shared
    0.13
    accessible
    0.12
    共享
    0.12
    shared
    0.11
     shared
    0.11
    共有
    0.11
    Shared
    0.11
    Accessible
    0.10
    _shared
    0.10
     Accessible
    0.10
    Activations Density 0.003%

    No Known Activations