© 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. 97680
    Prev
    Next
    INDEX
    Explanations

    Russian text

    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
     AMS
    -0.09
    ганда
    -0.08
    കൾ
    -0.08
     glaciers
    -0.08
    ுகள்
    -0.08
    ுகளில்
    -0.08
    rsat
    -0.08
    ongs
    -0.07
     ועד
    -0.07
     følger
    -0.07
    POSITIVE LOGITS
    ению
    0.16
    лению
    0.15
    ию
    0.14
    анию
    0.14
    тию
    0.13
    ованию
    0.12
    ству
    0.12
    енью
    0.11
    ирован
    0.10
    ительным
    0.10
    Activations Density 0.006%

    No Known Activations