© 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 EvalsExportsAPI 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. 20007
    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
    Hl
    -0.09
    rne
    -0.09
    ervation
    -0.08
     to
    -0.08
     than
    -0.08
     it
    -0.08
     likes
    -0.08
    ilarly
    -0.08
     assumption
    -0.08
    Rl
    -0.08
    POSITIVE LOGITS
     内容
    0.10
     四川
    0.10
     futhi
    0.09
     小说
    0.09
     Furthermore
    0.09
     Kapitel
    0.09
     关于
    0.09
     陈
    0.09
     中国
    0.09
     系
    0.08
    Activations Density 0.003%

    No Known Activations