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. 19343
    Prev
    Next
    INDEX
    Explanations

    Incenter and incircle

    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
     स्पष्ट
    -0.09
     klare
    -0.08
     USERS
    -0.08
     trả
    -0.08
     Clear
    -0.08
     kurzer
    -0.08
     Header
    -0.08
     Heidel
    -0.08
     ARRAY
    -0.08
     Chunk
    -0.08
    POSITIVE LOGITS
     gasket
    0.08
     pockets
    0.08
    /internal
    0.08
    stitial
    0.08
     της
    0.08
    _radius
    0.08
    iversal
    0.08
     кухни
    0.08
     courtyard
    0.08
    radius
    0.08
    Activations Density 0.009%

    No Known Activations