© 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. 71093
    Prev
    Next
    INDEX
    Explanations

    Tokenomics

    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
     Auge
    -0.09
     Igre
    -0.09
    kvæmt
    -0.08
     올해
    -0.08
     brighten
    -0.08
    改单
    -0.08
     escog
    -0.08
     Angelina
    -0.08
    מנות
    -0.08
     Katherine
    -0.08
    POSITIVE LOGITS
     scen
    0.08
     Starter
    0.08
     scenario
    0.07
     QA
    0.07
     للم
    0.07
     initial
    0.07
     viết
    0.07
    .Support
    0.07
     ಉತ್ಪ
    0.07
     holder
    0.07
    Activations Density 0.006%

    No Known Activations