© 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. 102891
    Prev
    Next
    INDEX
    Explanations

    4

    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
    achta
    -0.09
    enced
    -0.09
     cũng
    -0.09
    ":↵↵
    -0.09
    ifica
    -0.08
    itized
    -0.08
    ificar
    -0.08
     అద
    -0.08
     basta
    -0.08
     nawet
    -0.08
    POSITIVE LOGITS
    ....↵
    0.10
    ...↵
    0.10
     ...↵
    0.09
     …↵
    0.09
     ....↵
    0.09
     เป็นต้น
    0.09
     ..↵
    0.09
    (...)↵
    0.09
    .....↵
    0.08
    ・・・↵
    0.08
    Activations Density 0.005%

    No Known Activations