© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 103263
    Prev
    Next
    INDEX
    Explanations

    Croatia/Serbia

    np_max-act-logits · gemini-2.0-flash
    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
    Ruby
    -0.11
     ruby
    -0.10
     Louisiana
    -0.09
     Ruby
    -0.09
     Massachusetts
    -0.09
     Japanese
    -0.09
    ruby
    -0.09
     california
    -0.09
     Maine
    -0.09
     Boston
    -0.08
    POSITIVE LOGITS
     Croatia
    0.23
     hrvats
    0.22
     Serbian
    0.22
     Serbia
    0.21
     Croatian
    0.21
     Srbij
    0.20
    ović
    0.20
     Srbije
    0.20
     Hrvats
    0.20
     Hrvatskoj
    0.20
    Activations Density 0.042%

    No Known Activations