© 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. 71015
    Prev
    Next
    INDEX
    Explanations

    compression

    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
    ỏ
    -0.09
    lios
    -0.08
     놓
    -0.08
    職
    -0.08
     Justice
    -0.08
     kiek
    -0.08
     tær
    -0.07
     mest
    -0.07
     ock
    -0.07
     tabletop
    -0.07
    POSITIVE LOGITS
     compression
    0.20
    gzip
    0.19
     gzip
    0.19
    compression
    0.18
     Compression
    0.18
    Compress
    0.18
    .compress
    0.18
    Compression
    0.18
     compress
    0.17
     Compress
    0.17
    Activations Density 0.012%

    No Known Activations