Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130832
    Prev
    Next
    INDEX
    Explanations

    Coffee

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vsp
    -0.07
    <U
    -0.07
     المستخدم
    -0.07
     curly
    -0.07
    idu
    -0.07
    (U
    -0.07
    817
    -0.07
    лок
    -0.07
    126
    -0.07
     galvan
    -0.07
    POSITIVE LOGITS
    	cr
    0.08
    ょう
    0.08
     xen
    0.08
     feast
    0.08
     hydrate
    0.07
     wurde
    0.07
     क्र
    0.07
     Sat
    0.07
    enticate
    0.07
     đạo
    0.07
    Activations Density 0.001%

    No Known Activations