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. 43872
    Prev
    Next
    INDEX
    Explanations

    theater production

    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
     Binance
    -0.11
     개인정보
    -0.10
     Gmail
    -0.10
     Bitcoin
    -0.10
     Coinbase
    -0.10
    商城
    -0.10
     gmail
    -0.09
     Litecoin
    -0.09
     Xiaomi
    -0.09
     Zillow
    -0.09
    POSITIVE LOGITS
     dramatur
    0.16
     teatral
    0.15
     थिए
    0.14
     спектак
    0.13
     теат
    0.13
     rehearsal
    0.13
     공연
    0.13
     Theatre
    0.13
     Théâtre
    0.13
     teatr
    0.13
    Activations Density 0.128%

    No Known Activations