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. 48989
    Prev
    Next
    INDEX
    Explanations

    curls

    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
     cranes
    -0.08
    agawa
    -0.08
    erana
    -0.07
    .XR
    -0.07
     stelde
    -0.07
    (),"
    -0.07
    UMENT
    -0.07
    uiu
    -0.07
     deduct
    -0.07
    ுவர்
    -0.07
    POSITIVE LOGITS
     Oromo
    0.10
     irregular
    0.09
    宝宝
    0.08
     embraces
    0.08
     curls
    0.08
     propensity
    0.08
     soulful
    0.08
     abraz
    0.08
    flakes
    0.08
    orks
    0.08
    Activations Density 0.007%

    No Known Activations