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. 54038
    Prev
    Next
    INDEX
    Explanations

    Portugal

    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
     marche
    -0.09
     UCLA
    -0.08
     Iy
    -0.08
     Sper
    -0.08
    雪
    -0.08
     trast
    -0.08
     reduct
    -0.08
     CME
    -0.07
    reise
    -0.07
     federal
    -0.07
    POSITIVE LOGITS
     Portugal
    0.10
     Portuguese
    0.10
    Portugal
    0.09
    萄
    0.09
     Lisbon
    0.08
     brasileiro
    0.08
     bestowed
    0.08
    葡
    0.08
     portuguesa
    0.08
     português
    0.08
    Activations Density 0.013%

    No Known Activations