© 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. 19891
    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
    Necessary
    -0.10
     tych
    -0.09
     żad
    -0.08
    Sibling
    -0.08
     важных
    -0.08
     important
    -0.08
     şol
    -0.08
     никаких
    -0.08
     belangrijk
    -0.08
     anyone
    -0.08
    POSITIVE LOGITS
    004
    0.24
    002
    0.23
    006
    0.23
    005
    0.23
    014
    0.22
    003
    0.22
    008
    0.22
    001
    0.22
    017
    0.21
    013
    0.21
    Activations Density 0.003%

    No Known Activations