© 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. 7914
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    ขึ้น
    -0.08
     Tym
    -0.08
     whole
    -0.07
     Clover
    -0.07
     Nas
    -0.07
     remarkable
    -0.07
     സ്റ്റ
    -0.07
     surviving
    -0.07
     നിർ
    -0.07
     Mandarin
    -0.07
    POSITIVE LOGITS
    掉
    0.09
    Theory
    0.08
    Canceled
    0.08
    0.08
    Cancellation
    0.07
    /AIDS
    0.07
    You're
    0.07
    Philip
    0.07
    062
    0.07
    pst
    0.07
    Activations Density 0.594%

    No Known Activations