© 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. 19-RESID-POST-AA
    11. 103260
    Prev
    Next
    INDEX
    Explanations

    instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     의해
    -0.10
     Ձեր
    -0.10
     თქვენს
    -0.09
     ваше
    -0.09
     вашим
    -0.09
     ձեր
    -0.09
     вашему
    -0.09
     upravo
    -0.09
     ներկայ
    -0.09
     בעקבות
    -0.09
    POSITIVE LOGITS
     instructions
    0.17
    instructions
    0.14
     Instructions
    0.14
     advice
    0.14
     instrucciones
    0.14
     detailing
    0.14
     recommendations
    0.14
     details
    0.14
     specifying
    0.13
     Details
    0.13
    Activations Density 0.036%

    No Known Activations