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. 78539
    Prev
    Next
    INDEX
    Explanations

    plus sign

    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
     stomp
    -0.08
    overwrite
    -0.08
     overwrite
    -0.07
     furthermore
    -0.07
     eingel
    -0.07
     על
    -0.07
    -story
    -0.07
     проект
    -0.07
    etaan
    -0.07
     endorse
    -0.07
    POSITIVE LOGITS
    _split
    0.09
     parç
    0.09
     separación
    0.08
     usable
    0.08
     يف
    0.08
     separates
    0.08
     مستقل
    0.08
    自在
    0.08
     pits
    0.08
     þing
    0.08
    Activations Density 0.006%

    No Known Activations