© 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. 18286
    Prev
    Next
    INDEX
    Explanations

    Foreign media words

    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
     Bitcoins
    -0.10
     Saturdays
    -0.10
     Darth
    -0.10
     bitcoins
    -0.10
     Bitcoin
    -0.10
     Mondays
    -0.09
     Kindle
    -0.09
     Sundays
    -0.08
     Buddhism
    -0.08
     roses
    -0.08
    POSITIVE LOGITS
     multimedia
    0.12
     pollut
    0.11
     മാധ്യമ
    0.11
     મીડિયા
    0.11
     మీడియాలో
    0.11
     respective
    0.11
     animaux
    0.11
     మీడియ
    0.11
     genoemde
    0.10
     pollutants
    0.10
    Activations Density 0.236%

    No Known Activations