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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 60903
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    。如
    -0.08
    检
    -0.07
     ~~
    -0.07
     compreh
    -0.07
     SMART
    -0.07
    ার্স
    -0.07
     Willkommen
    -0.07
     পরীক্ষা
    -0.07
    合法
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    極
    0.09
    _PERCENT
    0.08
    severity
    0.08
     ihop
    0.08
    -et
    0.08
    이가
    0.08
    éditeur
    0.08
    极
    0.08
    afety
    0.08
    tní
    0.08
    Activations Density 0.099%

    No Known Activations