© 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. 521
    Prev
    Next
    INDEX
    Explanations

    .

    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
     Elementary
    -0.08
     задан
    -0.08
     Apenas
    -0.08
     Lin
    -0.08
     এবার
    -0.07
    BCD
    -0.07
     použ
    -0.07
    strand
    -0.07
     ellipt
    -0.07
     después
    -0.07
    POSITIVE LOGITS
    。此外
    0.10
    。而
    0.09
    Moreover
    0.08
    。另外
    0.08
     Moreover
    0.08
    形成
    0.08
    ကို
    0.08
    嘉
    0.08
     برا
    0.07
     પ્રવ
    0.07
    Activations Density 0.127%

    No Known Activations