© 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. 22040
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     that
    -0.09
     RTWF
    -0.09
    that
    -0.09
    	that
    -0.08
     χρήση
    -0.08
     توس
    -0.08
     الحفاظ
    -0.08
     الذي
    -0.08
    ائحة
    -0.08
    ussels
    -0.08
    POSITIVE LOGITS
     -
    0.10
     dominant
    0.09
    ,
    0.09
    -,
    0.09
     và
    0.08
     आणि
    0.08
    Domin
    0.08
     participating
    0.08
    -dollar
    0.08
     és
    0.08
    Activations Density 0.018%

    No Known Activations