© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 94618
    Prev
    Next
    INDEX
    Explanations

    #include

    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
     implant
    -0.09
    iex
    -0.08
     Implant
    -0.08
     kokoa
    -0.08
     implants
    -0.08
    xcf
    -0.08
    Capital
    -0.08
    _sorted
    -0.08
     หลัง
    -0.08
    avior
    -0.08
    POSITIVE LOGITS
    .temperature
    0.12
    Humidity
    0.12
     humidity
    0.11
    报告
    0.11
    humidity
    0.11
     pollutants
    0.11
     temperature
    0.11
     ताप
    0.10
     temperatura
    0.10
     температуры
    0.10
    Activations Density 0.008%

    No Known Activations