Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 111883
    Prev
    Next
    INDEX
    Explanations

    insurance

    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
     asio
    -0.08
    -0.08
     cérémon
    -0.08
     UNESCO
    -0.08
     schaffen
    -0.08
     plonge
    -0.07
     confinement
    -0.07
     cérémonie
    -0.07
    وز
    -0.07
     Potential
    -0.07
    POSITIVE LOGITS
    dogs
    0.09
     gods
    0.08
    会社
    0.08
    lastname
    0.08
    dog
    0.08
     વધારે
    0.08
     Giovanni
    0.08
    _company
    0.08
     garage
    0.08
    company
    0.08
    Activations Density 0.015%

    No Known Activations