© 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. 71180
    Prev
    Next
    INDEX
    Explanations

    holding items

    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
     Ton
    -0.08
     impeccable
    -0.07
     DIF
    -0.07
    qiq
    -0.07
    Aa
    -0.07
     Exceptional
    -0.07
     exceptional
    -0.07
     impecc
    -0.07
    haul
    -0.07
     Domin
    -0.07
    POSITIVE LOGITS
    REL
    0.09
    sgál
    0.08
     dispense
    0.08
     overnight
    0.08
     sord
    0.08
    下载安装
    0.08
     headset
    0.08
    习近平
    0.07
     disclose
    0.07
     svg
    0.07
    Activations Density 0.000%

    No Known Activations