© 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. 30843
    Prev
    Next
    INDEX
    Explanations

    Cooking/baking utensils

    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
    STREAM
    -0.08
     yaşayan
    -0.08
     theory
    -0.08
     Sheldon
    -0.08
    Enh
    -0.08
     Theory
    -0.08
     enhancing
    -0.08
    _stream
    -0.08
    GPS
    -0.07
    .zip
    -0.07
    POSITIVE LOGITS
     debajo
    0.09
    boven
    0.09
     भोजन
    0.08
     reposition
    0.08
    ชม
    0.08
    巡视
    0.08
     joystick
    0.08
     kaikke
    0.08
    hões
    0.08
    -bodied
    0.08
    Activations Density 0.014%

    No Known Activations