© 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. 19145
    Prev
    Next
    INDEX
    Explanations

    Parsing math problems

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Alibaba
    -0.10
    ;)↵↵
    -0.09
     أبريل
    -0.09
     сіз
    -0.08
     kiddos
    -0.08
     https
    -0.08
     =)
    -0.08
     നിങ്ങൾ
    -0.08
    Thanks
    -0.08
     ;)↵↵
    -0.08
    POSITIVE LOGITS
     whose
    0.14
    	that
    0.11
    whose
    0.10
    	when
    0.10
     cuya
    0.10
     والذي
    0.09
     cuyo
    0.09
     cuja
    0.09
    	finally
    0.09
     wanda
    0.09
    Activations Density 0.043%

    No Known Activations