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. 43265
    Prev
    Next
    INDEX
    Explanations

    soccer

    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
     Ю
    -0.08
    ன்
    -0.08
     Av
    -0.08
     最新
    -0.08
    历
    -0.07
     Parse
    -0.07
     av
    -0.07
     Apr
    -0.07
    .av
    -0.07
    云
    -0.07
    POSITIVE LOGITS
    Protocols
    0.09
    Podcast
    0.08
     origen
    0.08
     �
    0.08
     panorama
    0.08
     provoking
    0.08
    Toast
    0.08
     originate
    0.08
     bijzondere
    0.08
    Нач
    0.08
    Activations Density 0.007%

    No Known Activations