© 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. 19-RESID-POST-AA
    11. 19943
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GLFW
    -0.09
     Welch
    -0.08
     Fonts
    -0.08
     adjectives
    -0.08
    /fonts
    -0.08
     ques
    -0.08
    785
    -0.08
     サイズ
    -0.08
     Einst
    -0.08
    相关新闻
    -0.08
    POSITIVE LOGITS
     flows
    0.15
    流程
    0.15
    flows
    0.14
     flow
    0.14
    Flows
    0.14
     Flow
    0.13
    (flow
    0.13
     workflows
    0.13
    Flow
    0.13
     흐
    0.13
    Activations Density 0.023%

    No Known Activations