© 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. 11-RESID-POST-AA
    11. 65570
    Prev
    Next
    INDEX
    Explanations

    Transliterations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mecanismo
    -0.10
     caratter
    -0.09
    ателям
    -0.08
     Capitals
    -0.08
    наки
    -0.08
    سسة
    -0.08
    ottest
    -0.08
     Include
    -0.08
    атель
    -0.08
     Making
    -0.08
    POSITIVE LOGITS
     μό
    0.07
    ૉ
    0.07
    лай
    0.07
     FOB
    0.07
    umulator
    0.07
    ส์
    0.07
     та
    0.07
     hun
    0.07
     кей
    0.07
     verändert
    0.07
    Activations Density 0.041%

    No Known Activations