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. 15-RESID-POST-AA
    6. 72
    Prev
    Next
    INDEX
    Explanations

    step in different languages

    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
    也是
    -0.08
     müsse
    -0.08
     alojamiento
    -0.08
     هایی
    -0.08
    هایی
    -0.08
    ,args
    -0.08
     آورد
    -0.08
    ‌هایی
    -0.08
     perro
    -0.07
     өзі
    -0.07
    POSITIVE LOGITS
     Step
    0.13
     acima
    0.13
     step
    0.12
    步骤
    0.12
    Step
    0.12
     Schritt
    0.12
     above
    0.11
    一步
    0.10
    _step
    0.10
     tadi
    0.10
    Activations Density 0.007%

    No Known Activations