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. 58890
    Prev
    Next
    INDEX
    Explanations

    Oscar

    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
    hy
    -0.08
     irq
    -0.08
     TOR
    -0.08
    Sehr
    -0.07
    TEL
    -0.07
     übertragen
    -0.07
     tel
    -0.07
     hive
    -0.07
    tructure
    -0.07
     ве
    -0.07
    POSITIVE LOGITS
     prestig
    0.08
     famously
    0.08
     blockbuster
    0.08
     theatr
    0.08
     filmmaker
    0.08
    明星
    0.08
     थिए
    0.08
    影片
    0.08
     commentator
    0.08
     Poet
    0.08
    Activations Density 0.007%

    No Known Activations