© 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. 95344
    Prev
    Next
    INDEX
    Explanations

    respectively

    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
    现场
    -0.08
     التع
    -0.08
     కూడ
    -0.07
    ，很
    -0.07
    户
    -0.07
     ఉన్న
    -0.07
    موال
    -0.07
    ，非常
    -0.07
     duer
    -0.07
    ules
    -0.07
    POSITIVE LOGITS
    hma
    0.08
    ansion
    0.07
     fet
    0.07
     translations
    0.07
    Tracker
    0.07
     potenc
    0.07
     TA
    0.07
     vascular
    0.07
    Bow
    0.07
     Cakes
    0.07
    Activations Density 0.004%

    No Known Activations