© 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. 111503
    Prev
    Next
    INDEX
    Explanations

    arrangements and combinatorics

    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
    hler
    -0.08
     korist
    -0.08
    عيد
    -0.08
     Ebook
    -0.07
    hide
    -0.07
     Bedeutung
    -0.07
     humane
    -0.07
    sap
    -0.07
    swiper
    -0.07
     dnia
    -0.07
    POSITIVE LOGITS
     เล
    0.08
    opleft
    0.08
     решили
    0.08
     Missile
    0.07
    เลือก
    0.07
     donut
    0.07
    0.07
     selects
    0.07
     решил
    0.07
     placeholders
    0.07
    Activations Density 0.036%
    No Known Activations