© 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. 108272
    Prev
    Next
    INDEX
    Explanations

    silver

    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
     Restaurant
    -0.08
     பாத
    -0.08
    ortal
    -0.08
    —they
    -0.08
    margin
    -0.08
    rhs
    -0.08
     Real
    -0.07
    <Real
    -0.07
     hab
    -0.07
    usy
    -0.07
    POSITIVE LOGITS
     years
    0.10
    Years
    0.10
    年龄
    0.10
     tuổi
    0.10
     сед
    0.09
     الشيخ
    0.09
     年
    0.09
     usia
    0.09
     decades
    0.09
     उम्र
    0.09
    Activations Density 0.003%

    No Known Activations