© 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. 110518
    Prev
    Next
    INDEX
    Explanations

    show

    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
     MS
    -0.07
    imbo
    -0.07
    ibern
    -0.07
     Foods
    -0.07
    (all
    -0.07
     inmun
    -0.07
    �
    -0.07
    .Stored
    -0.07
     calculations
    -0.07
     suspected
    -0.07
    POSITIVE LOGITS
     premiums
    0.10
    مين
    0.09
     signage
    0.08
    Footer
    0.08
     download
    0.08
     téléchargement
    0.08
     دانلود
    0.08
    料金
    0.08
    Download
    0.08
    Foi
    0.08
    Activations Density 0.002%

    No Known Activations