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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 119297
    Prev
    Next
    INDEX
    Explanations

    Unilever

    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
    CARD
    -0.09
     tü
    -0.08
    终于
    -0.08
    机动车
    -0.08
    cards
    -0.07
    bewijs
    -0.07
    出了
    -0.07
    GR
    -0.07
     excursions
    -0.07
    .zone
    -0.07
    POSITIVE LOGITS
     multicultural
    0.09
     sip
    0.08
     Indonesia
    0.08
     multilingual
    0.08
     detergent
    0.08
    Brands
    0.08
     amph
    0.08
     Angola
    0.08
     Senegal
    0.08
    .rgb
    0.08
    Activations Density 0.002%

    No Known Activations