© 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 EvalsExportsinterp-engineNEWAPI 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. 69927
    Prev
    Next
    INDEX
    Explanations

    flight booking

    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
     phosphorylation
    -0.10
    ensus
    -0.09
    gpio
    -0.09
     GPIO
    -0.09
    Italic
    -0.08
    gradation
    -0.08
     UART
    -0.08
     BMP
    -0.08
    _gpio
    -0.08
     infiltration
    -0.08
    POSITIVE LOGITS
     airfare
    0.16
     Expedia
    0.15
     cheapest
    0.15
     airlines
    0.14
     airline
    0.14
    旅行
    0.14
     travelers
    0.13
     travel
    0.13
     여행
    0.13
     Travel
    0.13
    Activations Density 0.105%

    No Known Activations