© 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. 78096
    Prev
    Next
    INDEX
    Explanations

    product descriptions

    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
    inti
    -0.08
     inatt
    -0.08
     restaurants
    -0.08
     rhythms
    -0.08
     verra
    -0.08
    aping
    -0.08
     scriptures
    -0.07
     civilizations
    -0.07
    statistics
    -0.07
    ialect
    -0.07
    POSITIVE LOGITS
     купить
    0.10
    售价
    0.10
    送料無料
    0.10
     товары
    0.10
    Item
    0.10
     kostet
    0.09
     buchen
    0.09
    .amazon
    0.09
     товара
    0.09
    卖
    0.09
    Activations Density 0.144%

    No Known Activations