© 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. 19837
    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
     valgt
    -0.09
    selected
    -0.08
    Dto
    -0.08
     violating
    -0.08
     geselect
    -0.08
     انواع
    -0.08
     데이터를
    -0.08
     violate
    -0.08
     Daten
    -0.08
     selected
    -0.08
    POSITIVE LOGITS
    制度
    0.17
    完善
    0.16
    建设
    0.15
    保障
    0.15
    机制
    0.14
     mechanisms
    0.13
    改革
    0.13
     마련
    0.13
     safeguards
    0.13
     conducive
    0.12
    Activations Density 0.014%

    No Known Activations