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. 130941
    Prev
    Next
    INDEX
    Explanations

    �

    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
    �
    -0.08
    adzi
    -0.08
     النهاية
    -0.08
    ಂಡ್
    -0.08
    しか
    -0.08
     masquer
    -0.07
     proves
    -0.07
     বিরুদ্ধে
    -0.07
     Duchess
    -0.07
    واة
    -0.07
    POSITIVE LOGITS
    �
    0.09
    require
    0.09
     music
    0.08
     phare
    0.07
    Kt
    0.07
     лид
    0.07
    follow
    0.07
    im
    0.07
    increment
    0.07
     difficult
    0.07
    Activations Density 0.001%

    No Known Activations