© 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. 19686
    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
    -standard
    -0.10
    -focused
    -0.10
    -writing
    -0.09
    more
    -0.09
    -social
    -0.09
     hơn
    -0.09
     lebih
    -0.09
     più
    -0.09
    -language
    -0.09
    -changing
    -0.08
    POSITIVE LOGITS
     संभावना
    0.13
     будет
    0.13
     izango
    0.12
     olacaktır
    0.12
     احتمال
    0.12
     خواهید
    0.11
     oportunidad
    0.11
     হবে
    0.11
     خواهد
    0.11
     likely
    0.11
    Activations Density 0.009%

    No Known Activations