© 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. 21397
    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
     gyfer
    -0.11
    ห่ง
    -0.07
     settembre
    -0.07
    gadas
    -0.07
    within
    -0.07
     veces
    -0.07
     mewn
    -0.07
    ივე
    -0.07
    წყ
    -0.07
     ידי
    -0.07
    POSITIVE LOGITS
     on
    0.51
    	on
    0.42
     على
    0.37
    _on
    0.36
    .on
    0.33
    On
    0.33
     ऑन
    0.32
     på
    0.31
     On
    0.29
     pada
    0.29
    Activations Density 0.176%

    No Known Activations