© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64342
    Prev
    Next
    INDEX
    Explanations

    Berry

    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
    ulación
    -0.09
     spectacle
    -0.08
     leed
    -0.08
     Monat
    -0.08
     collapsed
    -0.07
    qrt
    -0.07
     rigu
    -0.07
     over
    -0.07
    ULATION
    -0.07
    Scaled
    -0.07
    POSITIVE LOGITS
    against
    0.09
    г
    0.08
    -angular
    0.08
    Decrypt
    0.08
     resistant
    0.08
    -resistant
    0.08
    hoes
    0.08
     Commun
    0.08
     Parliamentary
    0.08
     warriors
    0.08
    Activations Density 0.004%

    No Known Activations