© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 113483
    Prev
    Next
    INDEX
    Explanations

    raise

    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
     planes
    -0.09
     respectively
    -0.09
     قدم
    -0.08
     حص
    -0.08
     شمال
    -0.08
     apporte
    -0.08
    onnes
    -0.08
     enroll
    -0.07
     remercie
    -0.07
    uttet
    -0.07
    POSITIVE LOGITS
     poka
    0.09
    PDO
    0.08
    plicht
    0.08
    klan
    0.08
    rors
    0.08
    vard
    0.07
     subito
    0.07
    broker
    0.07
     əm
    0.07
    бук
    0.07
    Activations Density 0.001%

    No Known Activations