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. 98257
    Prev
    Next
    INDEX
    Explanations

    digits

    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
     म्हणजे
    -0.08
    .exc
    -0.07
     Bok
    -0.07
    ís
    -0.07
    ----------↵
    -0.07
     అంటే
    -0.07
     trif
    -0.07
     incurs
    -0.07
    exc
    -0.07
     Hybrid
    -0.07
    POSITIVE LOGITS
     famously
    0.11
     famous
    0.09
    stretch
    0.09
     beroemde
    0.08
     masterpiece
    0.08
    ളം
    0.08
     ergo
    0.08
     iconic
    0.08
    Creators
    0.08
    Evidence
    0.08
    Activations Density 0.031%

    No Known Activations