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. 55949
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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
     chopping
    -0.08
    -carb
    -0.08
     Caroline
    -0.08
     dibujo
    -0.08
     Anglo
    -0.08
     hardworking
    -0.08
     ordeal
    -0.08
     drankje
    -0.08
     drawers
    -0.07
     tasty
    -0.07
    POSITIVE LOGITS
    ̈
    0.11
    _Msk
    0.09
     versus
    0.09
     তৈ
    0.08
    য়ে
    0.08
    Mb
    0.08
     _____
    0.08
     ____
    0.08
     কী
    0.08
     Vers
    0.07
    Activations Density 0.076%

    No Known Activations