© 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. 22193
    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
    edian
    -0.09
    LOB
    -0.08
    vuldig
    -0.08
    ่วย
    -0.08
     nostri
    -0.08
    adecimal
    -0.08
    caled
    -0.08
     miei
    -0.08
    ariye
    -0.08
     своему
    -0.07
    POSITIVE LOGITS
     it's
    0.19
     you
    0.18
     it
    0.15
     there's
    0.14
     você
    0.14
     ನೀವು
    0.14
     நீங்கள்
    0.13
     તમે
    0.13
     আপনি
    0.13
     നിങ്ങൾ
    0.13
    Activations Density 0.006%

    No Known Activations