© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 110137
    Prev
    Next
    INDEX
    Explanations

    new world/era

    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
    ailable
    -0.08
     handy
    -0.08
    OLUME
    -0.08
    atud
    -0.07
     വർ
    -0.07
    ար�
    -0.07
     adicional
    -0.07
     knack
    -0.07
    เพิ่ม
    -0.07
     courtesy
    -0.07
    POSITIVE LOGITS
     foundation
    0.09
     방향
    0.09
     réforme
    0.09
     реформ
    0.09
     versão
    0.09
     foundations
    0.09
     reform
    0.08
     Alli
    0.08
     모습
    0.08
    renew
    0.08
    Activations Density 0.054%

    No Known Activations