© 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. 11-RESID-POST-AA
    6. 94442
    Prev
    Next
    INDEX
    Explanations

    (

    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
    ਾਵ
    -0.09
    ачи
    -0.08
     berichten
    -0.08
    臣
    -0.08
    Mang
    -0.07
     messen
    -0.07
    注意
    -0.07
    érées
    -0.07
    Tas
    -0.07
     zen
    -0.07
    POSITIVE LOGITS
     GOP
    0.09
     Newman
    0.08
     Christ
    0.08
     dop
    0.08
     vital
    0.07
    так
    0.07
     conocemos
    0.07
    −
    0.07
     conhe
    0.07
     location
    0.07
    Activations Density 0.019%

    No Known Activations