© 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. 95275
    Prev
    Next
    INDEX
    Explanations

    multiplication

    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
     Sharon
    -0.08
    /customer
    -0.08
    ুটি
    -0.08
    න්ත
    -0.08
     Angel
    -0.08
    ņēm
    -0.08
    iência
    -0.08
     aliquam
    -0.07
     Witt
    -0.07
     Kurz
    -0.07
    POSITIVE LOGITS
    สอบ
    0.09
     getest
    0.09
     bestät
    0.08
     confirm
    0.08
    Confirmed
    0.08
     Reviewed
    0.08
     Confirm
    0.08
     confirmed
    0.08
    確認
    0.08
     inaccur
    0.08
    Activations Density 0.059%

    No Known Activations