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. 11-RESID-POST-AA
    6. 12983
    Prev
    Next
    INDEX
    Explanations

    code or special 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
     dicha
    -0.08
     soared
    -0.07
     tali
    -0.07
    (idx
    -0.07
    (D
    -0.07
    (L
    -0.07
     дов
    -0.07
     añ
    -0.07
     consistently
    -0.07
    墨
    -0.07
    POSITIVE LOGITS
    лыгы
    0.08
    	pass
    0.08
     Pass
    0.08
    temporary
    0.07
     Passive
    0.07
    ත්ත
    0.07
     Chick
    0.07
     Duit
    0.07
     apparent
    0.07
     Luigi
    0.07
    Activations Density 0.000%

    No Known Activations