© 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. 22340
    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
    �្នាំ
    -0.09
    �览
    -0.09
     neat
    -0.09
    ��
    -0.09
     withdrew
    -0.09
    �្ន
    -0.09
    -vuot
    -0.09
    �េស
    -0.08
    ुळ
    -0.08
     калды
    -0.08
    POSITIVE LOGITS
     Bestandteil
    0.14
     to
    0.12
     part
    0.12
     onderdelen
    0.12
     parts
    0.12
     importance
    0.11
     onderdeel
    0.11
     اہم
    0.11
    Importance
    0.10
     부분
    0.10
    Activations Density 0.024%

    No Known Activations