© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 20613
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     우리는
    -0.11
     사례
    -0.09
     The
    -0.09
     정보
    -0.09
    -than
    -0.09
    .
    -0.09
     것이
    -0.09
     아무
    -0.08
    -mentioned
    -0.08
    를
    -0.08
    POSITIVE LOGITS
    ある
    0.17
    あり
    0.13
    できます
    0.11
    ない
    0.11
    続
    0.11
    ちな
    0.11
    ございます
    0.11
    ありません
    0.10
    あ
    0.10
    増
    0.10
    Activations Density 0.002%

    No Known Activations