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. 12938
    Prev
    Next
    INDEX
    Explanations

    Formulas

    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
    backup
    -0.08
    ข้อง
    -0.08
    deadline
    -0.08
    ูก
    -0.08
    educated
    -0.08
    ót
    -0.08
     துண
    -0.08
     verbinding
    -0.08
    اصر
    -0.08
     tidigare
    -0.08
    POSITIVE LOGITS
     vui
    0.09
     asynchronous
    0.08
     लोक
    0.08
     Atem
    0.07
     amino
    0.07
     reinforcement
    0.07
    _each
    0.07
     pynt
    0.07
     birbir
    0.07
    _sym
    0.07
    Activations Density 0.002%

    No Known Activations