© 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. 3-RESID-POST-AA
    11. 13414
    Prev
    Next
    INDEX
    Explanations

    batch files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     physiological
    -0.08
    孕
    -0.08
    мат
    -0.07
     физи
    -0.07
     wrest
    -0.07
    革命
    -0.07
     oste
    -0.07
    warming
    -0.07
     myst
    -0.07
     politicians
    -0.07
    POSITIVE LOGITS
     Komm
    0.09
     CMD
    0.09
    _COMMAND
    0.08
    েক্ষ
    0.08
     الفر
    0.08
     添
    0.08
    Clause
    0.08
     GAL
    0.08
     commandes
    0.08
     Commands
    0.08
    Activations Density 0.013%

    No Known Activations