© 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. 22046
    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
     الذين
    -0.11
    哪些
    -0.11
    uscious
    -0.10
    	if
    -0.10
     izay
    -0.10
    	that
    -0.09
     المزيد
    -0.09
    哪个
    -0.09
    ذين
    -0.09
    任何
    -0.09
    POSITIVE LOGITS
     being
    0.17
     být
    0.15
     być
    0.14
     essere
    0.14
     be
    0.14
     être
    0.14
     быть
    0.13
     byť
    0.13
     equals
    0.12
     étant
    0.12
    Activations Density 0.014%

    No Known Activations