© 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. 78364
    Prev
    Next
    INDEX
    Explanations

    more

    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
    قالات
    -0.08
    lend
    -0.08
    icum
    -0.08
    呢
    -0.08
    값
    -0.07
    projekt
    -0.07
    잡
    -0.07
     EX
    -0.07
    icione
    -0.07
     Помимо
    -0.07
    POSITIVE LOGITS
     sa
    0.07
     fé
    0.07
    879
    0.07
     sê
    0.07
     sang
    0.07
     virtue
    0.07
     saav
    0.07
    .stereotype
    0.07
     rā
    0.07
     erano
    0.07
    Activations Density 0.005%

    No Known Activations