© 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. 5450
    Prev
    Next
    INDEX
    Explanations

    Col

    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
     pide
    -0.07
     خ
    -0.07
     cht
    -0.07
     WEEK
    -0.07
     kind
    -0.07
    951
    -0.07
     хто
    -0.07
     bedoeling
    -0.07
     pneumonia
    -0.07
     لخ
    -0.07
    POSITIVE LOGITS
     Fiat
    0.08
     الفر
    0.08
    erton
    0.08
     Ames
    0.08
    izamos
    0.08
    orio
    0.07
     =)
    0.07
     sist
    0.07
    incy
    0.07
    anio
    0.07
    Activations Density 0.000%

    No Known Activations