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. 60970
    Prev
    Next
    INDEX
    Explanations

    Odysseus and Polyphemus story

    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
    /logout
    -0.09
     тора
    -0.08
     xl
    -0.08
     прием
    -0.08
     bảo
    -0.08
     आसपास
    -0.08
     ();
    ↵
    -0.08
    Around
    -0.07
    bounds
    -0.07
    ಯ್ಯ
    -0.07
    POSITIVE LOGITS
     SIZE
    0.07
     eid
    0.07
     dislike
    0.07
    stdlib
    0.07
    েকে
    0.07
     opp
    0.07
    στη
    0.07
     ASSERT
    0.07
     notoriously
    0.07
     generators
    0.07
    Activations Density 0.001%

    No Known Activations