© 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. 30412
    Prev
    Next
    INDEX
    Explanations

    Requests and offers

    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
    这样的
    -0.08
     stumbled
    -0.08
     adversely
    -0.08
     vaulted
    -0.08
    aufl
    -0.08
     welches
    -0.08
     같이
    -0.07
     Bones
    -0.07
    રૂ
    -0.07
    ా
    -0.07
    POSITIVE LOGITS
     вами
    0.08
     gamut
    0.07
     drainage
    0.07
    .pattern
    0.07
     abi
    0.07
    대로
    0.07
    景
    0.07
     Cim
    0.07
     patrón
    0.07
    全部
    0.07
    Activations Density 0.085%

    No Known Activations