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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1257
    Prev
    Next
    INDEX
    Explanations

    Lagrange multipliers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    American
    -0.08
     مم
    -0.08
     Chevron
    -0.07
     lama
    -0.07
     �
    -0.07
    bj
    -0.07
     quiet
    -0.07
     Inf
    -0.07
    lege
    -0.07
     الو
    -0.07
    POSITIVE LOGITS
     matric
    0.09
    記事
    0.08
     vitre
    0.08
     страниц
    0.07
     вик
    0.07
    ß
    0.07
    ucid
    0.07
     Dl
    0.07
     metabolites
    0.07
     Trent
    0.07
    Activations Density 0.002%

    No Known Activations