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

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 102334
    Prev
    Next
    INDEX
    Explanations

    triangles and vertices

    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
    Not in Any Lists

    No Comments

    Negative Logits
     molta
    -0.07
     rhai
    -0.07
     forskning
    -0.07
     onderzoek
    -0.07
    ())).
    -0.07
     hopeful
    -0.07
    gist
    -0.07
     gist
    -0.07
     hoffen
    -0.07
     CAGR
    -0.07
    POSITIVE LOGITS
    .vertices
    0.10
    -induced
    0.10
    -prev
    0.09
    -treated
    0.09
     与
    0.09
    connecting
    0.09
    -created
    0.09
    vertices
    0.09
    -images
    0.09
     بمدينة
    0.09
    Activations Density 0.044%

    No Known Activations