© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47726
    Prev
    Next
    INDEX
    Explanations

    say "the ending атель"

    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
    ിസ
    -0.08
    イズ
    -0.08
    OCUS
    -0.08
    ским
    -0.08
    formatter
    -0.08
    ർമ
    -0.08
     برو
    -0.08
     хлоп
    -0.08
    ർക്ക
    -0.08
    สต์
    -0.08
    POSITIVE LOGITS
    атель
    0.15
    атели
    0.13
    ательная
    0.11
    ательной
    0.11
    ателя
    0.10
    ателей
    0.10
    ателю
    0.10
    ательно
    0.10
    ательное
    0.10
    անիշ
    0.10
    Activations Density 0.001%

    No Known Activations