© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 112375
    Prev
    Next
    INDEX
    Explanations

    age

    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
     plumbing
    -0.08
     בסיס
    -0.08
     inglês
    -0.07
    মূল
    -0.07
     padrão
    -0.07
     cables
    -0.07
     directions
    -0.07
     Plumbing
    -0.07
    漏
    -0.07
    ('|
    -0.07
    POSITIVE LOGITS
    年龄
    0.20
     edad
    0.20
    Edad
    0.18
     usia
    0.18
     idade
    0.18
     उम्र
    0.18
     ηλικ
    0.18
     ages
    0.17
     বয়স
    0.17
    Возраст
    0.16
    Activations Density 0.130%

    No Known Activations