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

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 99734
    Prev
    Next
    INDEX
    Explanations

    contradictions

    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
    lay
    -0.08
    niejsze
    -0.08
    lays
    -0.08
    优势
    -0.08
     специал
    -0.07
    enge
    -0.07
     rõ
    -0.07
     MOQ
    -0.07
    MOQ
    -0.07
    体验
    -0.07
    POSITIVE LOGITS
     rejecting
    0.09
     rechazo
    0.09
     rejects
    0.09
    不存在
    0.09
     rejet
    0.09
     rejected
    0.09
    Exists
    0.08
    Reject
    0.08
     ��
    0.08
     denies
    0.08
    Activations Density 0.010%

    No Known Activations