© 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. 23-RESID-POST-AA
    11. 48003
    Prev
    Next
    INDEX
    Explanations

    197

    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
    imer
    -0.08
     hourly
    -0.07
     Pract
    -0.07
     kilo
    -0.07
     dadurch
    -0.07
     stále
    -0.07
    န
    -0.07
     Estimated
    -0.07
     о
    -0.07
     Liter
    -0.07
    POSITIVE LOGITS
    Csv
    0.09
    CSV
    0.08
    יגה
    0.08
    Aj
    0.08
     sé
    0.08
    Vil
    0.08
     midway
    0.08
    DZ
    0.07
    Gl
    0.07
     occasione
    0.07
    Activations Density 0.000%

    No Known Activations