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. 12787
    Prev
    Next
    INDEX
    Explanations

    ava

    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
    -face
    -0.08
     Medikamente
    -0.08
    әд
    -0.08
     ари
    -0.08
     폭
    -0.08
    .SELECT
    -0.08
     groundwork
    -0.08
    Selections
    -0.08
     үнд
    -0.08
    ('../../../
    -0.08
    POSITIVE LOGITS
     fil
    0.08
     profesionales
    0.07
     enthusiasts
    0.07
    activities
    0.07
    Activity
    0.07
     professionals
    0.07
     Activity
    0.07
     camar
    0.07
     பதிவ
    0.07
     leaderboard
    0.07
    Activations Density 0.003%

    No Known Activations