© 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. 110184
    Prev
    Next
    INDEX
    Explanations

    timestamp

    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
     insiders
    -0.08
    రు
    -0.08
    _Unity
    -0.08
     πλα
    -0.07
     STL
    -0.07
    _CLIENT
    -0.07
    ('|
    -0.07
    .Mesh
    -0.07
    ('#
    -0.07
     Senhora
    -0.07
    POSITIVE LOGITS
     eternal
    0.08
     gig
    0.08
    amide
    0.08
     dane
    0.08
    成年
    0.08
    /feed
    0.07
     octave
    0.07
     mortal
    0.07
    �
    0.07
     Sams
    0.07
    Activations Density 0.002%

    No Known Activations