© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 21988
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     miatt
    -0.09
     keessa
    -0.09
    there
    -0.09
     there's
    -0.09
    áter
    -0.09
    ’époque
    -0.09
    especially
    -0.08
     there
    -0.08
    ביעה
    -0.08
    ?)↵
    -0.08
    POSITIVE LOGITS
     каждый
    0.12
     кажд
    0.12
     fiecare
    0.12
     každý
    0.11
     każdy
    0.11
     setiap
    0.10
     chaque
    0.10
     प्रत्येक
    0.10
     список
    0.10
     ഓരോ
    0.10
    Activations Density 0.001%

    No Known Activations