© 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 EvalsExportsinterp-engineNEWAPI 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. 18650
    Prev
    Next
    INDEX
    Explanations

    bf

    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
    &(
    -0.09
    ignore
    -0.08
    ag
    -0.08
    vänd
    -0.08
    )
    -0.08
     **
    -0.08
    tia
    -0.08
     emot
    -0.08
     their
    -0.08
    bies
    -0.08
    POSITIVE LOGITS
     подробнее
    0.10
    ЕР
    0.09
     INFORM
    0.09
    》，
    0.08
    ОД
    0.08
    _Ass
    0.08
     подроб
    0.08
     консульт
    0.08
    _;↵
    0.08
     расска
    0.08
    Activations Density 0.075%

    No Known Activations