© 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. 19540
    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
     kunne
    -0.12
     بتوان
    -0.11
     kunna
    -0.11
     permettra
    -0.10
     voisi
    -0.10
     voidaan
    -0.10
     पर्याप्त
    -0.10
     könnten
    -0.09
     можно
    -0.09
     смогут
    -0.09
    POSITIVE LOGITS
     Contrary
    0.12
     считается
    0.12
     convention
    0.11
     conventions
    0.11
     contrairement
    0.11
     tegenstelling
    0.11
     peculiar
    0.11
    Convention
    0.11
     принято
    0.10
     quirky
    0.10
    Activations Density 0.025%

    No Known Activations