© 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. 69221
    Prev
    Next
    INDEX
    Explanations

    communicate

    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
     Weg
    -0.08
    ushy
    -0.08
    zym
    -0.07
     discretion
    -0.07
     gaya
    -0.07
     hypertension
    -0.07
    asje
    -0.07
    anza
    -0.07
    weru
    -0.07
    ished
    -0.07
    POSITIVE LOGITS
     общения
    0.10
    通信
    0.09
     संवाद
    0.09
    Among
    0.09
     Comunicación
    0.09
     যোগাযোগ
    0.09
     Kommunikation
    0.09
     comunicação
    0.08
     communiceren
    0.08
     comunicación
    0.08
    Activations Density 0.006%

    No Known Activations