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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 102692
    Prev
    Next
    INDEX
    Explanations

    chakra

    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
     clone
    -0.08
     આગ
    -0.08
    .clone
    -0.08
     দিন
    -0.07
     dosta
    -0.07
    Protocol
    -0.07
    巧
    -0.07
    .encode
    -0.07
     observation
    -0.07
     intelligent
    -0.07
    POSITIVE LOGITS
     Journey
    0.08
     الرئيسية
    0.08
     compartments
    0.08
     kehilangan
    0.08
     Sep
    0.08
     നിറ
    0.08
     Pie
    0.08
    esinde
    0.08
     rempl
    0.08
    kses
    0.07
    Activations Density 0.003%

    No Known Activations