© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18484
    Prev
    Next
    INDEX
    Explanations

    piece

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المختلفة
    -0.09
    ίες
    -0.09
     farklı
    -0.09
    ительными
    -0.09
    ებზე
    -0.09
    igungen
    -0.09
    	else
    -0.09
    ებისთვის
    -0.08
    ۰
    -0.08
    ӡ
    -0.08
    POSITIVE LOGITS
    -of
    0.08
     of
    0.08
    stück
    0.08
     ofin
    0.07
    cut
    0.07
    **↵
    0.07
     unnoticed
    0.07
     خپل
    0.07
    -cut
    0.07
    0.07
    Activations Density 0.041%
    No Known Activations