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. 53926
    Prev
    Next
    INDEX
    Explanations

    Home screen widgets

    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
     comparatively
    -0.08
     pronunciation
    -0.08
    เอ็ด
    -0.08
     eyebrows
    -0.08
     moderately
    -0.07
     Herstellung
    -0.07
     moderate
    -0.07
    wiek
    -0.07
    wei
    -0.07
     vowels
    -0.07
    POSITIVE LOGITS
    布局
    0.09
    _tile
    0.09
    Wallpaper
    0.09
     customizable
    0.09
     wallpaper
    0.09
     personalization
    0.09
    widgets
    0.09
    .contains
    0.09
    _TILE
    0.08
     widgets
    0.08
    Activations Density 0.008%

    No Known Activations