© 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. 23-RESID-POST-AA
    11. 49931
    Prev
    Next
    INDEX
    Explanations

    technical/document-related

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estudos
    -0.08
     estudo
    -0.07
     mieć
    -0.07
    April
    -0.07
    ულ
    -0.07
    anjut
    -0.07
     משחק
    -0.07
     nä
    -0.07
     wakes
    -0.07
    wira
    -0.07
    POSITIVE LOGITS
    othesis
    0.07
    :text
    0.07
     Timothy
    0.07
    Recipient
    0.07
    legt
    0.07
     fuite
    0.07
     текста
    0.07
     బాల
    0.07
     AML
    0.07
    ителем
    0.07
    Activations Density 0.000%

    No Known Activations