Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98457
    Prev
    Next
    INDEX
    Explanations

    say "start"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .arraycopy
    -0.11
     abandoning
    -0.10
     quitté
    -0.10
     dejó
    -0.09
    індегі
    -0.09
     deixou
    -0.09
     deixam
    -0.09
     remplacer
    -0.09
    ಿನ್ನೆ
    -0.09
     abandonar
    -0.09
    POSITIVE LOGITS
    .start
    0.19
    .show
    0.15
    .mainloop
    0.15
     start
    0.14
    .run
    0.14
    .activate
    0.14
    启动
    0.13
    	start
    0.13
    .Start
    0.13
    .launch
    0.12
    Activations Density 0.011%

    No Known Activations