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. 130827
    Prev
    Next
    INDEX
    Explanations

    Racing context

    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
    .ft
    -0.08
     Ft
    -0.08
     yıld
    -0.08
    贡
    -0.08
     rostro
    -0.08
     चर्च
    -0.08
     यी
    -0.08
     Broadway
    -0.08
     tiz
    -0.08
     �
    -0.08
    POSITIVE LOGITS
     للت
    0.09
     赛车
    0.08
     السيارة
    0.08
     Motorsport
    0.08
    akisa
    0.08
    orghini
    0.08
    eneuve
    0.08
     pneus
    0.08
    Sport
    0.08
     Championship
    0.08
    Activations Density 0.006%

    No Known Activations