© 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. 19-RESID-POST-AA
    11. 20561
    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
     მუდმ
    -0.10
     მუდ
    -0.09
     შეუ�
    -0.09
    ჯახ
    -0.09
    ხმარ
    -0.09
     უწ
    -0.09
     ყოველთვის
    -0.09
     აუცილებლად
    -0.09
     սն
    -0.09
    მყოფ
    -0.09
    POSITIVE LOGITS
     target
    0.07
    0.07
    (entries
    0.07
     Hands
    0.07
    juju
    0.07
    (Icons
    0.07
    hands
    0.07
     entries
    0.07
     intérieure
    0.07
     عالمي
    0.07
    Activations Density 0.000%
    No Known Activations