Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130727
    Prev
    Next
    INDEX
    Explanations

    satellite data

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     নিরাপ
    -0.08
     ipad
    -0.08
     পুলিশ
    -0.08
     conect
    -0.08
     সত
    -0.08
     slowdown
    -0.08
     ekh
    -0.08
     പൊലീസ്
    -0.08
     stretching
    -0.08
     szám
    -0.07
    POSITIVE LOGITS
     astronaut
    0.09
     Presley
    0.08
     BED
    0.08
     رجل
    0.08
    .Pull
    0.07
     G
    0.07
     loko
    0.07
     borrowers
    0.07
    POCH
    0.07
     التغ
    0.07
    Activations Density 0.000%

    No Known Activations