© 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. 47583
    Prev
    Next
    INDEX
    Explanations

    ري

    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
     нагруз
    -0.08
     vyr
    -0.08
     �
    -0.07
    iał
    -0.07
     ase
    -0.07
     powerhouse
    -0.07
    arel
    -0.07
     AVR
    -0.07
    ély
    -0.07
     despe
    -0.07
    POSITIVE LOGITS
    طة
    0.12
    جون
    0.10
    جين
    0.09
    حت
    0.08
    ابون
    0.08
    مت
    0.08
     Deiner
    0.08
     esposa
    0.08
    டு
    0.08
    داً
    0.08
    Activations Density 0.001%

    No Known Activations