© 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. 110109
    Prev
    Next
    INDEX
    Explanations

    Greek mythology

    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
     eletrônico
    -0.08
    zinho
    -0.08
    路线
    -0.08
     elettron
    -0.08
    Starter
    -0.07
     blazer
    -0.07
    <meta
    -0.07
    Register
    -0.07
     bouquet
    -0.07
     nus
    -0.07
    POSITIVE LOGITS
     cliff
    0.09
     earthquakes
    0.08
     characterized
    0.07
    רג
    0.07
     sensitive
    0.07
     flooding
    0.07
     terrem
    0.07
     sampling
    0.07
     scal
    0.07
     liegt
    0.07
    Activations Density 0.002%

    No Known Activations