© 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. 19793
    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
     =
    -0.11
     same
    -0.11
     equals
    -0.11
     identical
    -0.10
    是真是假
    -0.10
     有没有
    -0.10
     ..↵↵
    -0.09
     ....↵↵
    -0.09
     başka
    -0.09
     ==
    -0.09
    POSITIVE LOGITS
    -ish
    0.20
    -like
    0.18
     teilweise
    0.17
    -esque
    0.17
     somewhat
    0.16
     parcialmente
    0.16
     partly
    0.16
     gedeelt
    0.16
     partially
    0.14
     deels
    0.14
    Activations Density 0.224%

    No Known Activations