© 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. 20745
    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
     大圣
    -0.11
     百家乐
    -0.11
    　据
    -0.10
     百乐
    -0.10
    ２０１
    -0.10
    》↵↵
    -0.10
    ՛
    -0.10
    　三
    -0.10
    >/
    -0.10
    ٢
    -0.10
    POSITIVE LOGITS
     אם
    0.25
     если
    0.23
     إذا
    0.23
     if
    0.23
     اگر
    0.21
     якщо
    0.21
     যদি
    0.21
     nếu
    0.20
     यदि
    0.20
     jeśli
    0.20
    Activations Density 0.060%

    No Known Activations