© 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. 47495
    Prev
    Next
    INDEX
    Explanations

    program code

    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
     zuh
    -0.10
     brz
    -0.09
     lesion
    -0.08
     yayi
    -0.08
     kwambiri
    -0.08
     zow
    -0.08
     zircon
    -0.08
     lumps
    -0.08
     clickable
    -0.08
     انف
    -0.08
    POSITIVE LOGITS
    architect
    0.08
     тепло
    0.08
    chapter
    0.08
    025
    0.07
     architectures
    0.07
    REFERENCE
    0.07
    AUTH
    0.07
    ोध
    0.07
     arquitect
    0.07
     архитект
    0.07
    Activations Density 0.001%

    No Known Activations