© 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. 21254
    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
     અથવા
    -0.10
     atau
    -0.09
     അല്ല
    -0.09
     किंवा
    -0.09
     ή
    -0.09
     veya
    -0.09
    ，对于
    -0.09
    情况下
    -0.09
     ಅಥವಾ
    -0.09
    情况
    -0.09
    POSITIVE LOGITS
     phrase
    0.16
     letterlijk
    0.15
     sentence
    0.15
     phrases
    0.15
     grammatical
    0.15
    _sentence
    0.15
     literalmente
    0.15
     literally
    0.15
     frase
    0.14
    phrase
    0.14
    Activations Density 0.018%

    No Known Activations