© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47665
    Prev
    Next
    INDEX
    Explanations

    hurricane

    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
     perf
    -0.10
    perf
    -0.09
    亚
    -0.09
    亞
    -0.08
     connex
    -0.08
    Perf
    -0.08
    鞋
    -0.08
     Perf
    -0.08
    香
    -0.08
    awah
    -0.08
    POSITIVE LOGITS
     storms
    0.15
     earthquakes
    0.13
     thunderstorms
    0.13
     hurricane
    0.13
    storms
    0.12
    _weather
    0.12
     floods
    0.12
     earthquake
    0.12
     hurricanes
    0.12
     סער
    0.12
    Activations Density 0.037%

    No Known Activations