© 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 EvalsExportsAPI 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. 20348
    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
     grundsätzlich
    -0.13
     unbedingt
    -0.12
     möglicherweise
    -0.12
     presumably
    -0.11
     potentially
    -0.11
     posiblemente
    -0.11
     kindlasti
    -0.11
     essentially
    -0.11
     반드시
    -0.11
     обязательно
    -0.10
    POSITIVE LOGITS
     nowadays
    0.18
     heutzutage
    0.16
     bý
    0.16
     бывает
    0.16
     tegenwoordig
    0.15
     brukar
    0.14
    곤
    0.14
     байдаг
    0.13
     suelen
    0.13
     suele
    0.13
    Activations Density 0.117%

    No Known Activations