Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 1570
    Prev
    Next
    INDEX
    Explanations

    CI

    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
    值
    -0.08
     Abuja
    -0.08
     jal
    -0.08
     Glaub
    -0.08
    逐
    -0.08
    �
    -0.07
    拍
    -0.07
    �
    -0.07
    Matcher
    -0.07
    价值
    -0.07
    POSITIVE LOGITS
    >[
    0.08
     خاطر
    0.08
     chemically
    0.08
    하게
    0.08
     خلا
    0.08
     Woodland
    0.07
    roya
    0.07
     restaurant
    0.07
    headed
    0.07
     회사
    0.07
    Activations Density 0.001%

    No Known Activations