© 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. 17897
    Prev
    Next
    INDEX
    Explanations

    OpenAI API usage examples

    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
    Negative Logits
    Derived
    -0.09
    Compatible
    -0.09
    ífico
    -0.09
     Derived
    -0.09
    Sortable
    -0.08
    ábado
    -0.08
     derived
    -0.08
     Writable
    -0.08
    Modified
    -0.08
    Separated
    -0.08
    POSITIVE LOGITS
     ↵↵  ↵↵
    0.08
    =input
    0.08
    >Hello
    0.08
    $email
    0.08
     　
    0.08
    INTRO
    0.08
    0.08
     ...…↵
    0.08
    @login
    0.08
    0.08
    Activations Density 0.003%
    No Known Activations