© 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. 11-RESID-POST-AA
    11. 71456
    Prev
    Next
    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     organisms
    -0.09
     pom
    -0.09
     dare
    -0.08
     PMID
    -0.08
     organizações
    -0.08
    操
    -0.07
     Task
    -0.07
     Täter
    -0.07
     phenotype
    -0.07
     logrado
    -0.07
    POSITIVE LOGITS
    brane
    0.09
    raison
    0.09
    _n
    0.08
    dx
    0.08
    geri
    0.08
    ram
    0.07
    jualan
    0.07
    grim
    0.07
    abilidade
    0.07
     deployed
    0.07
    Activations Density 0.000%

    No Known Activations