© 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. 11-RESID-POST-AA
    11. 44879
    Prev
    Next
    INDEX
    Explanations

    separators

    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
     అనే
    -0.08
    一样
    -0.08
    理由
    -0.08
    anches
    -0.08
    �
    -0.07
    క
    -0.07
    iz
    -0.07
     loopt
    -0.07
    价值
    -0.07
    -0.07
    POSITIVE LOGITS
     matrix
    0.08
     आम
    0.07
    matrix
    0.07
     cult
    0.07
     None
    0.07
     outlined
    0.07
    acetam
    0.07
    ോർ
    0.07
    不限
    0.07
    .Serial
    0.07
    Activations Density 0.087%

    No Known Activations