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. 76453
    Prev
    Next
    INDEX
    Explanations

    3

    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
     integrates
    -0.07
    Theory
    -0.07
    ↵↵//
    -0.07
     Im
    -0.07
     એટલે
    -0.07
     suy
    -0.07
     neighborhood
    -0.07
    ida
    -0.07
     네
    -0.06
    lung
    -0.06
    POSITIVE LOGITS
     الفنان
    0.08
     terken
    0.08
    scape
    0.08
    clearfix
    0.08
     kleuren
    0.08
    Кол
    0.08
    泄
    0.07
     gema
    0.07
     Clickfunnels
    0.07
    ्रीय
    0.07
    Activations Density 0.010%

    No Known Activations