© 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. 21405
    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
     uitvo
    -0.08
     talvez
    -0.08
    =.*
    -0.07
    -0.07
    amh
    -0.07
    .logo
    -0.07
     tarjo
    -0.07
     oan
    -0.07
     tini
    -0.07
     mukana
    -0.07
    POSITIVE LOGITS
     увеличить
    0.19
     aumentar
    0.18
     увелич
    0.18
     atraer
    0.17
     zwięks
    0.17
     attract
    0.17
     increase
    0.17
     attirer
    0.17
     attracts
    0.17
    吸
    0.16
    Activations Density 0.024%
    No Known Activations