© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111120
    Prev
    Next
    INDEX
    Explanations

    in

    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
    .strict
    -0.10
    .warning
    -0.08
     phases
    -0.08
     FG
    -0.08
     lbl
    -0.07
    .lbl
    -0.07
    .label
    -0.07
    (destination
    -0.07
     districts
    -0.07
     MGM
    -0.07
    POSITIVE LOGITS
    嬉
    0.08
     Porter
    0.08
     начин
    0.08
     Ende
    0.08
     uitstekend
    0.08
     Wett
    0.08
    compet
    0.07
     read
    0.07
    john
    0.07
    心得
    0.07
    Activations Density 0.007%

    No Known Activations