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. 74575
    Prev
    Next
    INDEX
    Explanations

    streaming

    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
     retourner
    -0.08
    Apis
    -0.07
    informat
    -0.07
    ște
    -0.07
     zeit
    -0.07
    neh
    -0.07
    ength
    -0.07
    伊
    -0.07
    जात
    -0.07
     Charger
    -0.07
    POSITIVE LOGITS
     seren
    0.08
     storm
    0.08
     Derecho
    0.08
     fotos
    0.07
    lighting
    0.07
     לנו
    0.07
    __))
    0.07
     عط
    0.07
     Storm
    0.07
    LIGHT
    0.07
    Activations Density 0.003%

    No Known Activations