© 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. 25100
    Prev
    Next
    INDEX
    Explanations

    with

    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
    یات
    -0.08
     Safe
    -0.08
     unsafe
    -0.08
    utzer
    -0.08
     Cpu
    -0.08
     Saf
    -0.08
     clocks
    -0.08
     দায়
    -0.08
    unsafe
    -0.08
    ディース
    -0.08
    POSITIVE LOGITS
     cyc
    0.08
    ->{$
    0.08
     UM
    0.07
     in
    0.07
    0.07
     with
    0.07
     regularly
    0.07
     part
    0.07
     торгов
    0.07
    عي
    0.07
    Activations Density 0.002%

    No Known Activations