© 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. 71496
    Prev
    Next
    INDEX
    Explanations

    panther

    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
     Leb
    -0.08
     Simpson
    -0.08
    arias
    -0.08
    ======
    -0.07
     Wine
    -0.07
     unnatural
    -0.07
     wine
    -0.07
    iece
    -0.07
     oil
    -0.07
     chores
    -0.07
    POSITIVE LOGITS
     veld
    0.08
    pk
    0.08
     qaz
    0.08
    �
    0.07
     안
    0.07
     mahdoll
    0.07
    _slug
    0.07
     bgcolor
    0.07
    кут
    0.07
     كې
    0.07
    Activations Density 0.001%

    No Known Activations