© 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. 23-RESID-POST-AA
    11. 49316
    Prev
    Next
    INDEX
    Explanations

    Clar

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uar
    -0.08
    ↵///
    -0.08
    ks
    -0.07
    uas
    -0.07
     duly
    -0.07
    ្រ�
    -0.07
    ksiyon
    -0.07
     Building
    -0.07
     paus
    -0.07
     humilde
    -0.07
    POSITIVE LOGITS
     ATI
    0.09
    ivati
    0.09
    ivate
    0.08
     intérêt
    0.08
    ATI
    0.08
     WELL
    0.08
    atás
    0.08
    itatem
    0.08
    atieve
    0.08
    abella
    0.08
    Activations Density 0.001%

    No Known Activations