© 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. 30231
    Prev
    Next
    INDEX
    Explanations

    n

    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
     flowing
    -0.09
     néanmoins
    -0.08
    aza
    -0.08
    azas
    -0.08
    Adding
    -0.08
    แน
    -0.07
    ಡೆಯ
    -0.07
    АЗ
    -0.07
    "ז
    -0.07
    Nevertheless
    -0.07
    POSITIVE LOGITS
     requiere
    0.08
     SAF
    0.08
     sori
    0.07
     individuos
    0.07
     YES
    0.07
     suna
    0.07
     japones
    0.07
     Japón
    0.07
     Fed
    0.07
     indivíduos
    0.07
    Activations Density 0.001%

    No Known Activations