© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 26296
    Prev
    Next
    INDEX
    Explanations

    Virgo

    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
     των
    -0.07
    flip
    -0.07
     graph
    -0.07
    Scanning
    -0.07
    reate
    -0.07
    alties
    -0.07
     Lor
    -0.07
    Graph
    -0.07
     Licensing
    -0.07
    Lor
    -0.07
    POSITIVE LOGITS
    午後
    0.09
     tomorrow
    0.08
     posição
    0.08
    \Carbon
    0.08
    િયન
    0.08
    ian
    0.08
    ನಲ್ಲಿ
    0.08
    柱
    0.08
    iano
    0.08
    inski
    0.08
    Activations Density 0.005%

    No Known Activations