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. 11-RESID-POST-AA
    6. 113020
    Prev
    Next
    INDEX
    Explanations

    Character relationships/pairings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     найдете
    -0.08
    .Elapsed
    -0.07
    -0.07
     Закон
    -0.07
    .Util
    -0.07
     εγκα
    -0.07
     яр
    -0.07
     функцию
    -0.07
     estarán
    -0.07
    овую
    -0.07
    POSITIVE LOGITS
     pair
    0.10
     femin
    0.10
     romant
    0.09
    pair
    0.09
     pasangan
    0.09
     pairs
    0.09
     combinations
    0.09
     fandom
    0.09
     parejas
    0.09
     זוג
    0.09
    Activations Density 0.049%

    No Known Activations