© 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. 6353
    Prev
    Next
    INDEX
    Explanations

    Foreign language adjectives

    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
     vastgesteld
    -0.10
     ऐसा
    -0.10
     specifiek
    -0.09
     असा
    -0.09
     gewen
    -0.09
    esteld
    -0.09
     vald
    -0.09
     nødvendig
    -0.09
    ikbaar
    -0.09
     ایسا
    -0.09
    POSITIVE LOGITS
     nakne
    0.19
     svenske
    0.17
     danske
    0.16
     erotiske
    0.16
     gamle
    0.16
     deilige
    0.15
     nye
    0.15
     norske
    0.15
     komplette
    0.15
     populære
    0.14
    Activations Density 0.003%

    No Known Activations