© 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. 21578
    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
     the
    -0.12
    :↵↵
    -0.08
    CREATE
    -0.08
    salary
    -0.07
     anyone
    -0.07
    ={↵
    -0.07
     THROW
    -0.07
    രി
    -0.07
    ommes
    -0.07
    olle
    -0.07
    POSITIVE LOGITS
     **
    0.10
    0.10
    ック
    0.08
     ժ
    0.08
    ’nın
    0.08
    _EDEFAULT
    0.08
    ーブ
    0.08
    нознач
    0.08
    -ի
    0.07
     ներ�
    0.07
    Activations Density 0.029%
    No Known Activations