© 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. 21926
    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
    ňe
    -0.08
     permettant
    -0.08
    Specify
    -0.07
     allowing
    -0.07
    자인
    -0.07
    ંત્ર
    -0.07
     zuk
    -0.07
    CTION
    -0.07
    Allow
    -0.07
    ňiz
    -0.07
    POSITIVE LOGITS
     halluc
    0.19
     occasionally
    0.15
     inaccuracies
    0.14
    错误
    0.14
    输出
    0.14
     иногда
    0.14
     manchmal
    0.13
     incorrectly
    0.13
     Occasionally
    0.13
     output
    0.13
    Activations Density 0.014%

    No Known Activations