© 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. 19-RESID-POST-AA
    11. 102226
    Prev
    Next
    INDEX
    Explanations

    start

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    下载安装
    -0.08
     preset
    -0.07
    Installation
    -0.07
     دادن
    -0.07
     trigger
    -0.07
    -0.07
     تحميل
    -0.07
    Trigger
    -0.07
     Unterricht
    -0.07
     Bukkit
    -0.07
    POSITIVE LOGITS
     fintech
    0.14
     founders
    0.14
     εται
    0.13
     incub
    0.13
     biotech
    0.13
     startups
    0.13
     companies
    0.13
     కంపెన
    0.13
     કંપની
    0.13
    公司
    0.13
    Activations Density 0.008%
    No Known Activations