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. 98561
    Prev
    Next
    INDEX
    Explanations

    Unicode character

    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
    ированные
    -0.09
    ированных
    -0.08
    定
    -0.08
    ार्ट
    -0.08
    ствуют
    -0.08
    ствовать
    -0.08
     ideal
    -0.08
    ्ड
    -0.08
    ированный
    -0.08
    rụ
    -0.07
    POSITIVE LOGITS
    �
    0.12
    �
    0.11
    �
    0.09
    చ
    0.09
     Manning
    0.08
    ଚ
    0.08
    ಿಚ
    0.08
    ಚ
    0.08
    -op
    0.08
    очной
    0.08
    Activations Density 0.001%

    No Known Activations