© 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 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. 69273
    Prev
    Next
    INDEX
    Explanations

    routes

    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
    resent
    -0.08
     installers
    -0.08
     keessatti
    -0.07
    -0.07
     present
    -0.07
     drugih
    -0.07
     noreferrer
    -0.07
     הרב
    -0.07
     ٻين
    -0.07
     miiran
    -0.07
    POSITIVE LOGITS
    ిద
    0.09
    明
    0.08
    _pts
    0.08
    화를
    0.08
    (ctx
    0.08
    화
    0.07
    _problem
    0.07
     जाग
    0.07
     사고
    0.07
    (Task
    0.07
    Activations Density 0.000%
    No Known Activations