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

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 49213
    Prev
    Next
    INDEX
    Explanations

    say "độ"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �ษ
    -0.08
    की
    -0.08
    েক্ষ
    -0.08
    esson
    -0.08
     تش
    -0.08
    사
    -0.07
    cia
    -0.07
     limpeza
    -0.07
     والن
    -0.07
     Interaction
    -0.07
    POSITIVE LOGITS
     độ
    0.12
    ંધ
    0.08
     وب
    0.08
    önet
    0.08
     postoje
    0.08
    .Root
    0.08
    øð
    0.08
    ou
    0.08
    .root
    0.07
    도
    0.07
    Activations Density 0.000%

    No Known Activations