© 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. 6613
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     مدريد
    -0.13
     dowl
    -0.12
     portada
    -0.11
    年底
    -0.11
     hoofdstad
    -0.11
     madrid
    -0.11
     Ausbildung
    -0.11
     poveč
    -0.11
     oktober
    -0.11
     أكتوبر
    -0.10
    POSITIVE LOGITS
    ъа
    0.15
    ъи
    0.13
     qho
    0.12
    0.12
    чү
    0.12
    phi
    0.11
     ભગ
    0.11
    ̉
    0.11
     mutant
    0.11
    чиком
    0.11
    Activations Density 0.677%

    No Known Activations