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. 9093
    Prev
    Next
    INDEX
    Explanations

    A

    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
     आ
    -0.08
     ряд
    -0.08
    บ
    -0.08
     Edwards
    -0.07
    工程
    -0.07
     इंज
    -0.07
    ن
    -0.07
     reinst
    -0.07
     ख
    -0.07
    摩
    -0.07
    POSITIVE LOGITS
     Madh
    0.08
    size
    0.08
    wah
    0.07
    Beat
    0.07
     dad
    0.07
     dorsal
    0.07
     microw
    0.07
     నాయక
    0.07
     centr
    0.07
     outr
    0.07
    Activations Density 0.140%

    No Known Activations