© 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. 18585
    Prev
    Next
    INDEX
    Explanations

    through (in different 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
     যেখানে
    -0.09
     যা
    -0.09
     identifying
    -0.09
     detecting
    -0.08
     waarin
    -0.08
     אשר
    -0.08
     কিছু
    -0.08
     assessing
    -0.08
     waarbij
    -0.07
     такую
    -0.07
    POSITIVE LOGITS
     through
    0.12
     mediante
    0.11
     attraverso
    0.11
     melalui
    0.10
     במסגרת
    0.10
     بواسطة
    0.10
     توسط
    0.10
     ద్వారా
    0.10
     через
    0.10
     durch
    0.10
    Activations Density 0.038%

    No Known Activations