© 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. 20547
    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
    аще
    -0.09
     implementations
    -0.08
    essential
    -0.08
    ienza
    -0.07
    Generally
    -0.07
    .Base
    -0.07
     чаще
    -0.07
     broadly
    -0.07
     generell
    -0.07
    。例如
    -0.06
    POSITIVE LOGITS
     mention
    0.20
     mentioning
    0.19
     mentions
    0.17
     envolvendo
    0.16
    mention
    0.16
     involving
    0.16
     incorporating
    0.16
     incorporate
    0.15
     incorporar
    0.15
     kuhusu
    0.15
    Activations Density 0.121%

    No Known Activations