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. 76436
    Prev
    Next
    INDEX
    Explanations

    content length, social media

    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
     видов
    -0.08
     Fernando
    -0.08
     licensors
    -0.08
    公安
    -0.08
     ECS
    -0.08
    'Union
    -0.08
     fabricant
    -0.08
     chemically
    -0.08
    recogn
    -0.08
     extérieur
    -0.08
    POSITIVE LOGITS
     langere
    0.10
     Longer
    0.10
     longer
    0.10
     deeper
    0.08
     длин
    0.08
     المقال
    0.08
     lengthy
    0.08
    uah
    0.08
     titled
    0.08
     किताब
    0.08
    Activations Density 0.015%

    No Known Activations