© 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. 11-RESID-POST-AA
    11. 113589
    Prev
    Next
    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gle
    -0.09
     såd
    -0.08
     hamper
    -0.07
    픈
    -0.07
     ultra
    -0.07
    그
    -0.07
     Raphael
    -0.07
     von
    -0.07
     eller
    -0.07
    ్బ
    -0.07
    POSITIVE LOGITS
    549
    0.09
    глав
    0.08
    227
    0.08
    остав
    0.08
     Kin
    0.08
    ुख
    0.08
    颜
    0.07
    Глав
    0.07
    ��
    0.07
    ंख
    0.07
    Activations Density 0.003%

    No Known Activations