© 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. 22264
    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
     olika
    -0.11
     разных
    -0.11
    ованием
    -0.11
    ”며
    -0.11
     უფრო
    -0.10
     médec
    -0.10
     უკეთ
    -0.10
     სხვადასხვა
    -0.10
     বিভিন্ন
    -0.10
     სხვადას
    -0.10
    POSITIVE LOGITS
     Anzahl
    0.18
     количество
    0.17
     number
    0.17
     میزان
    0.15
     число
    0.15
     amount
    0.15
    number
    0.14
     ಮಟ್ಟ
    0.14
     jumlah
    0.14
    Number
    0.14
    Activations Density 0.013%

    No Known Activations