© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18142
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
     없다
    -0.08
    _same
    -0.08
     of
    -0.08
     same
    -0.08
     similarly
    -0.08
     or
    -0.07
    同
    -0.07
     �
    -0.07
     Same
    -0.07
     it's
    -0.07
    POSITIVE LOGITS
    Regarding
    0.10
     dependendo
    0.09
    	snprintf
    0.09
    Estim
    0.09
    Depending
    0.09
     calculating
    0.09
     cuja
    0.09
     Regarding
    0.09
     rough
    0.09
     calcula
    0.09
    Activations Density 0.028%

    No Known Activations