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. 98101
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
     autonomous
    -0.11
    лів
    -0.08
     semplice
    -0.08
    овано
    -0.08
    но
    -0.08
     Прост
    -0.08
    redirect
    -0.08
    biased
    -0.07
     Sk
    -0.07
    лип
    -0.07
    POSITIVE LOGITS
    úrg
    0.08
     fille
    0.08
     satt
    0.08
     シャ
    0.08
     آی
    0.08
    アル
    0.08
    áticos
    0.08
     종료
    0.07
     njen
    0.07
     चाहे
    0.07
    Activations Density 0.000%

    No Known Activations