© 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. 11-RESID-POST-AA
    11. 54790
    Prev
    Next
    INDEX
    Explanations

    differential equations

    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
     ala
    -0.07
    Or
    -0.07
    .ed
    -0.07
     rol
    -0.07
     Berger
    -0.07
    .reducer
    -0.07
    ربي
    -0.07
     ter
    -0.07
    Lip
    -0.07
    -0.07
    POSITIVE LOGITS
    fork
    0.08
     réussite
    0.08
    aciju
    0.07
     researches
    0.07
    upo
    0.07
     fondamentale
    0.07
     Zv
    0.07
     自
    0.07
    646
    0.07
     fortuna
    0.07
    Activations Density 0.001%
    No Known Activations