© 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. 19620
    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
    yyval
    -0.09
     beant
    -0.08
     orgas
    -0.08
     cellul
    -0.08
     cellulose
    -0.08
     suhte
    -0.08
     Euchar
    -0.08
     anatomy
    -0.07
    	sprintf
    -0.07
     болох
    -0.07
    POSITIVE LOGITS
    (nums
    0.20
     nums
    0.18
    nums
    0.16
    (numbers
    0.14
    数组
    0.14
    _nums
    0.13
     array
    0.13
     arr
    0.12
    .array
    0.12
     inorder
    0.12
    Activations Density 0.017%

    No Known Activations