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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2575
    Prev
    Next
    INDEX
    Explanations

    Motors

    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
     ಮು
    -0.09
    vine
    -0.09
     topp
    -0.08
     hype
    -0.08
     Ske
    -0.08
     ترك
    -0.07
    عادة
    -0.07
     துண
    -0.07
    vpn
    -0.07
     Davenport
    -0.07
    POSITIVE LOGITS
     Fig
    0.08
    inos
    0.08
     Ew
    0.07
    0.07
    stava
    0.07
    com
    0.07
     BF
    0.07
    asikan
    0.07
    days
    0.07
     teng
    0.07
    Activations Density 0.004%
    No Known Activations