© 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. 19779
    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
     dealer
    -0.12
     Monopoly
    -0.12
     Chrysler
    -0.11
     Montessori
    -0.11
     gallons
    -0.11
     Porsche
    -0.11
     furniture
    -0.11
     tarot
    -0.11
     showroom
    -0.11
     dealers
    -0.11
    POSITIVE LOGITS
     genome
    0.24
     fasta
    0.23
     genomic
    0.23
    _gene
    0.23
    Protein
    0.22
     RNA
    0.22
     gene
    0.22
     SNP
    0.22
     nucleotide
    0.22
     protein
    0.22
    Activations Density 0.030%

    No Known Activations