© 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. 23-RESID-POST-AA
    11. 50704
    Prev
    Next
    INDEX
    Explanations

    er

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    insp
    -0.09
     stanov
    -0.08
     Recruit
    -0.08
    inc
    -0.08
     SPI
    -0.08
    ిస్త
    -0.08
     spi
    -0.08
    Ell
    -0.08
    িনী
    -0.07
    hnte
    -0.07
    POSITIVE LOGITS
    asers
    0.21
    aser
    0.18
    asures
    0.16
    asing
    0.14
    asure
    0.11
    ases
    0.11
    asion
    0.11
    േസ
    0.10
    asured
    0.10
    blems
    0.10
    Activations Density 0.002%

    No Known Activations