© 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. 110113
    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
    awarkan
    -0.08
     bals
    -0.08
    (mon
    -0.08
     �
    -0.07
    ವರಿಗೆ
    -0.07
    ميم
    -0.07
    whatever
    -0.07
    ವರು
    -0.07
    烟
    -0.07
     multicast
    -0.07
    POSITIVE LOGITS
    ico
    0.08
     airplane
    0.08
     transporter
    0.07
    /cgi
    0.07
    ीक
    0.07
    örn
    0.07
    iciário
    0.07
     Air
    0.07
     واست
    0.07
     stating
    0.07
    Activations Density 0.001%

    No Known Activations