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. 90080
    Prev
    Next
    INDEX
    Explanations

    bullet points

    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
     temperatura
    -0.09
     Electro
    -0.08
    immungen
    -0.08
     темпера
    -0.08
     lids
    -0.08
     célé
    -0.08
    imshow
    -0.08
     sensibilidad
    -0.08
     température
    -0.08
     ताप
    -0.08
    POSITIVE LOGITS
     bullet
    0.14
     bullets
    0.12
     Bullet
    0.11
    bullet
    0.11
    列表
    0.11
    Bullet
    0.10
    ITEM
    0.10
     सूची
    0.09
     �
    0.09
     списка
    0.09
    Activations Density 0.022%

    No Known Activations