© 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. 19-RESID-POST-AA
    11. 102668
    Prev
    Next
    INDEX
    Explanations

    methods

    np_max-act-logits · gemini-2.0-flash
    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
    ammlung
    -0.09
    יהול
    -0.08
     sorting
    -0.08
     translation
    -0.08
     bediening
    -0.08
    izing
    -0.08
     изготовления
    -0.08
    translation
    -0.08
     handling
    -0.08
     uitvoering
    -0.08
    POSITIVE LOGITS
    方式
    0.24
    方法
    0.20
     방법
    0.19
     방식
    0.18
    机制
    0.18
    过程
    0.18
    措施
    0.18
    方案
    0.17
     ವಿಧಾನ
    0.16
     રીત
    0.16
    Activations Density 0.085%

    No Known Activations