© 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. 23-RESID-POST-AA
    11. 52022
    Prev
    Next
    INDEX
    Explanations

    commas and "and"

    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
    Negative Logits
     Management
    -0.09
    ув
    -0.08
    Management
    -0.08
     Empres
    -0.08
    شار
    -0.08
     Business
    -0.08
     doğr
    -0.07
    гуул
    -0.07
     zakelijke
    -0.07
     gouvernement
    -0.07
    POSITIVE LOGITS
     budgets
    0.15
    预算
    0.14
     бюдж
    0.13
     бюджета
    0.13
     timelines
    0.13
     бюджет
    0.12
     road
    0.12
     बज
    0.12
     budget
    0.12
     büt
    0.12
    Activations Density 0.051%

    No Known Activations