© 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. 96277
    Prev
    Next
    INDEX
    Explanations

    üünü

    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
     olunur
    -0.13
    됩니다
    -0.13
    されています
    -0.13
     wordt
    -0.12
    되어
    -0.12
    され
    -0.11
     осуществляется
    -0.11
     بنایا
    -0.11
     қилин
    -0.11
     geschaffen
    -0.11
    POSITIVE LOGITS
     aldı
    0.12
     görmek
    0.12
     almak
    0.12
    zd
    0.11
     okum
    0.11
     azalt
    0.11
     merke
    0.11
     seven
    0.10
    za
    0.10
     değişt
    0.10
    Activations Density 0.006%

    No Known Activations