© 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. 3-RESID-POST-AA
    11. 13029
    Prev
    Next
    INDEX
    Explanations

    CNC

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.10
    সূ
    -0.08
    طف
    -0.08
     Childhood
    -0.07
    十分
    -0.07
     intimate
    -0.07
     Anderson
    -0.07
    _MUT
    -0.07
    大家
    -0.07
    였다
    -0.07
    POSITIVE LOGITS
     CNC
    0.08
     conto
    0.08
     страх
    0.07
     разработки
    0.07
     Haus
    0.07
    415
    0.07
    Qa
    0.07
     sette
    0.07
    CCC
    0.07
     nut
    0.07
    Activations Density 0.002%
    No Known Activations