© 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. 3-RESID-POST-AA
    11. 13260
    Prev
    Next
    INDEX
    Explanations

    Schema

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deney
    -0.08
    über
    -0.08
    plot
    -0.07
     CONTRIBUTORS
    -0.07
    पूर्व
    -0.07
     MMM
    -0.07
     Hunts
    -0.07
     Ор
    -0.07
     пищи
    -0.07
     Compass
    -0.07
    POSITIVE LOGITS
    AW
    0.07
     confl
    0.07
     rivol
    0.07
    �
    0.07
    大的
    0.07
     slavery
    0.07
    Ve
    0.07
     AW
    0.07
    白
    0.07
     conference
    0.07
    Activations Density 0.001%

    No Known Activations