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. 58505
    Prev
    Next
    INDEX
    Explanations

    solve

    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
    READY
    -0.08
     Majesty
    -0.08
     പ്രക
    -0.08
     양
    -0.08
     अनुर
    -0.08
     glycol
    -0.07
    anha
    -0.07
    -0.07
     Yah
    -0.07
     haut
    -0.07
    POSITIVE LOGITS
     mysteries
    0.10
     problems
    0.10
     problemas
    0.09
     проблемы
    0.08
     puzzles
    0.08
     задачи
    0.08
     Problems
    0.08
     constipation
    0.08
    .solve
    0.08
    不了
    0.07
    Activations Density 0.026%

    No Known Activations