© 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. 11-RESID-POST-AA
    11. 91567
    Prev
    Next
    INDEX
    Explanations

    code or foreign snippet

    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
     spacecraft
    -0.09
    人数
    -0.09
     astronaut
    -0.09
     Willem
    -0.08
     acceler
    -0.08
     Viewing
    -0.08
     بر
    -0.08
    教師
    -0.08
     교수
    -0.08
     Nom
    -0.08
    POSITIVE LOGITS
    (function
    0.11
     jquery
    0.10
    ("^
    0.10
     sass
    0.10
    jquery
    0.10
     plugin
    0.09
     AJAX
    0.08
    (":
    0.08
    bower
    0.08
    ajax
    0.08
    Activations Density 0.006%

    No Known Activations