© 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. 47807
    Prev
    Next
    INDEX
    Explanations

    Italian language

    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
    ásticas
    -0.10
    utada
    -0.09
    ITES
    -0.09
     դրանք
    -0.09
     madura
    -0.09
    ustada
    -0.09
     اهي
    -0.09
    uretat
    -0.08
    ћи
    -0.08
     nzira
    -0.08
    POSITIVE LOGITS
    ato
    0.15
    ativo
    0.13
    abile
    0.12
    izzato
    0.12
    aneo
    0.12
    ante
    0.11
    ale
    0.11
    issimo
    0.11
    atorio
    0.10
    dato
    0.10
    Activations Density 0.005%

    No Known Activations