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. 98459
    Prev
    Next
    INDEX
    Explanations

    .exec commands

    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
    ाछ
    -0.09
     kece
    -0.08
    čia
    -0.08
    チャ
    -0.07
     hablan
    -0.07
    583
    -0.07
    lecture
    -0.07
    ाफी
    -0.07
    אלה
    -0.07
     vergro
    -0.07
    POSITIVE LOGITS
    .exec
    0.18
     exec
    0.17
    exec
    0.15
    .exit
    0.14
    .run
    0.13
    _exec
    0.13
    .mainloop
    0.13
     exit
    0.13
     run
    0.13
    .Exit
    0.13
    Activations Density 0.003%

    No Known Activations