© 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. 19-RESID-POST-AA
    11. 22485
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avelmente
    -0.10
     Different
    -0.10
    loxacin
    -0.09
    uline
    -0.09
     verschillende
    -0.09
    ácie
    -0.09
     Natuurlijk
    -0.09
    (piece
    -0.08
     forskjellige
    -0.08
    manın
    -0.08
    POSITIVE LOGITS
    SD
    0.11
    CI
    0.11
    To
    0.10
    KS
    0.10
    P
    0.10
    OK
    0.10
    CH
    0.10
    TC
    0.10
    IC
    0.10
    G
    0.10
    Activations Density 0.025%

    No Known Activations