© 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. 23-RESID-POST-AA
    11. 6626
    Prev
    Next
    INDEX
    Explanations

    math theorems

    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
    ati
    -0.08
     suffer
    -0.08
     preferable
    -0.08
    amus
    -0.07
    的
    -0.07
    atus
    -0.07
    catch
    -0.07
     એ
    -0.07
     యొక్క
    -0.07
    auxite
    -0.07
    POSITIVE LOGITS
     experts
    0.08
    .Err
    0.08
    ňuje
    0.08
    [assembly
    0.08
     mixtures
    0.08
     čís
    0.08
    িযোগ
    0.08
    ให
    0.08
     mixture
    0.08
     computerized
    0.07
    Activations Density 0.001%

    No Known Activations