© 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. 71472
    Prev
    Next
    INDEX
    Explanations

    MLS

    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
     thanksgiving
    -0.09
     luister
    -0.08
    เดิน
    -0.08
     děti
    -0.08
     confessed
    -0.08
     пайд
    -0.08
     ย
    -0.08
     Xavier
    -0.08
     aloud
    -0.08
     epsilon
    -0.08
    POSITIVE LOGITS
     Std
    0.10
    ®
    0.09
     electronically
    0.08
    ®,
    0.08
    wx
    0.08
    联盟
    0.08
    (IS
    0.08
     ©
    0.07
    Alliance
    0.07
    vo
    0.07
    Activations Density 0.012%

    No Known Activations