© 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. 23-RESID-POST-AA
    11. 47912
    Prev
    Next
    INDEX
    Explanations

    countries

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     funcionario
    -0.12
     funcionarios
    -0.11
     usuario
    -0.10
     horario
    -0.10
     aniversario
    -0.10
     anuncio
    -0.10
     instancia
    -0.10
     diario
    -0.10
     criterio
    -0.10
     anuncios
    -0.10
    POSITIVE LOGITS
     Rússia
    0.11
     Tail
    0.11
     Paragu
    0.10
     Alemanha
    0.10
     França
    0.10
     Bolí
    0.10
     Nig
    0.10
     Gr
    0.10
     Tanz
    0.10
     Índia
    0.10
    Activations Density 0.004%

    No Known Activations