© 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 EvalsExportsAPI 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. 21162
    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
     (
    -0.15
    0
    -0.13
    2
    -0.11
    1
    -0.11
     as
    -0.10
    4
    -0.10
    3
    -0.09
    5
    -0.09
     approximately
    -0.09
     is
    -0.09
    POSITIVE LOGITS
    հանուր
    0.13
    ഴിക്കോട്
    0.13
    ,Moda
    0.13
    хыра
    0.12
     շահ
    0.12
    რგან
    0.12
    հան
    0.12
    0.12
    য়ামী
    0.12
    әыб
    0.12
    Activations Density 0.013%
    No Known Activations