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. 60995
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    irlpool
    -0.07
    :s
    -0.07
    -fluid
    -0.07
    vine
    -0.07
     Nutrition
    -0.07
     został
    -0.07
    irde
    -0.07
    طع
    -0.07
    würd
    -0.07
    :d
    -0.07
    POSITIVE LOGITS
     ranging
    0.10
     varies
    0.08
     үйл
    0.08
     varying
    0.08
     مواقع
    0.08
     manieren
    0.08
     cara
    0.08
     моделей
    0.08
     manier
    0.08
     сайтов
    0.08
    Activations Density 0.096%

    No Known Activations