© 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. 11-RESID-POST-AA
    11. 942
    Prev
    Next
    INDEX
    Explanations

    megabytes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Notice
    -0.08
    .public
    -0.08
     öffentliche
    -0.08
    .tom
    -0.08
    textarea
    -0.08
    Mary
    -0.08
    шу
    -0.07
    .ma
    -0.07
     Tiny
    -0.07
    公告
    -0.07
    POSITIVE LOGITS
    ai
    0.08
     Jak
    0.08
     ai
    0.08
     Entre
    0.08
    uib
    0.07
     ratings
    0.07
    urrences
    0.07
     рейтинг
    0.07
     episod
    0.07
     Divide
    0.07
    Activations Density 0.004%

    No Known Activations