© 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. 21566
    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
    ушылар
    -0.09
    赢家
    -0.09
    扒开
    -0.09
    мақта
    -0.09
    удың
    -0.09
    ушы
    -0.09
    赛马会
    -0.08
    قتل
    -0.08
    風吹けば
    -0.08
    彼
    -0.08
    POSITIVE LOGITS
    特点
    0.25
    情况
    0.22
     characteristics
    0.20
     características
    0.18
     상황
    0.18
     특징
    0.17
     పరిస్థిత
    0.17
     caratteristiche
    0.17
    状
    0.17
     характерист
    0.17
    Activations Density 0.026%

    No Known Activations