© 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. 3-RESID-POST-AA
    11. 1192
    Prev
    Next
    INDEX
    Explanations

    force

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    раз
    -0.08
    među
    -0.08
     sincerely
    -0.08
     repel
    -0.08
     affair
    -0.08
    Pocket
    -0.08
     имущества
    -0.07
     caracteriza
    -0.07
     endure
    -0.07
     pocket
    -0.07
    POSITIVE LOGITS
     Legion
    0.08
     Pour
    0.08
     Upt
    0.07
     curvature
    0.07
    atil
    0.07
     Iraq
    0.07
     软件
    0.07
    .cy
    0.07
     foreground
    0.07
     kosong
    0.07
    Activations Density 0.000%

    No Known Activations