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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 19070
    Prev
    Next
    INDEX
    Explanations

    period

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alot
    -0.10
    ,因此
    -0.09
     때문에
    -0.09
     cuz
    -0.08
     টাকা
    -0.08
     suele
    -0.08
     dolar
    -0.08
    했고
    -0.08
     phenomenal
    -0.08
    /show
    -0.08
    POSITIVE LOGITS
     découvrez
    0.12
     Découvrez
    0.11
    Découvrez
    0.11
     Lorem
    0.10
     Designed
    0.10
     Your
    0.10
     entdecken
    0.10
    Lorem
    0.10
     discover
    0.09
     descubre
    0.09
    Activations Density 0.016%

    No Known Activations