© 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 EvalsExportsinterp-engineNEWAPI 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. 22077
    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
    _that
    -0.09
     Registered
    -0.08
     finances
    -0.08
    ITOS
    -0.08
    Damit
    -0.08
     그것
    -0.07
     recherches
    -0.07
    -that
    -0.07
     Articles
    -0.07
     Effective
    -0.07
    POSITIVE LOGITS
    牲交
    0.11
    �讯
    0.10
    机官网
    0.10
    虎机
    0.10
    超碰
    0.09
    跑狗
    0.09
    刷流水
    0.09
    �ერ
    0.09
    ��
    0.09
     посколь
    0.09
    Activations Density 0.023%

    No Known Activations