© 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. 19035
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
     samting
    -0.10
     ដែល
    -0.10
     terwijl
    -0.10
     Terwijl
    -0.09
     jika
    -0.09
    	while
    -0.09
     mentre
    -0.09
     যেমন
    -0.09
    ៊ុន
    -0.09
     habang
    -0.09
    POSITIVE LOGITS
     وبعض
    0.16
     quelques
    0.12
    、一
    0.11
     काही
    0.11
    一个
    0.11
     ഒരു
    0.11
     몇
    0.11
     alguns
    0.11
     algumas
    0.11
     beaucoup
    0.11
    Activations Density 0.047%

    No Known Activations