© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 112731
    Prev
    Next
    INDEX
    Explanations

    travel itineraries

    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
     Wallace
    -0.08
    branch
    -0.08
     duct
    -0.08
     Aguil
    -0.08
     शाख
    -0.08
     Aner
    -0.08
     Erkennt
    -0.08
     Schäden
    -0.08
    _unicode
    -0.08
     وانت
    -0.08
    POSITIVE LOGITS
     itinerary
    0.19
    安排
    0.16
     schedule
    0.14
     આયોજન
    0.14
     journée
    0.13
     schedules
    0.13
    Schedule
    0.13
     распис
    0.13
     하루
    0.12
    .daily
    0.12
    Activations Density 0.121%

    No Known Activations