© 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. 3-RESID-POST-AA
    11. 12845
    Prev
    Next
    INDEX
    Explanations

    import

    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
    立即
    -0.09
     ফলে
    -0.09
     zie
    -0.08
     kana
    -0.08
     Dadurch
    -0.07
     Alta
    -0.07
     waardoor
    -0.07
     wodurch
    -0.07
    Naam
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     труда
    0.08
     fø
    0.08
    ­
    0.07
    ീയ
    0.07
    0.07
     admi
    0.07
     playlist
    0.07
     rounding
    0.07
     Eb
    0.07
     trá
    0.07
    Activations Density 0.000%
    No Known Activations