© 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. 6474
    Prev
    Next
    INDEX
    Explanations

    file operations

    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
    Adjusted
    -0.11
    .adjust
    -0.10
    _authenticated
    -0.10
    .authenticate
    -0.10
    Authenticated
    -0.10
    _adjust
    -0.10
    .train
    -0.10
    _specific
    -0.09
    Defined
    -0.09
    _active
    -0.09
    POSITIVE LOGITS
    การ
    0.19
     verzending
    0.16
     việc
    0.15
     การ
    0.15
     чт
    0.15
     обработки
    0.14
     создание
    0.14
     получение
    0.14
     удаления
    0.14
     выполнение
    0.14
    Activations Density 0.047%

    No Known Activations