© 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. 47792
    Prev
    Next
    INDEX
    Explanations

    Director/General

    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
    ithand
    -0.08
    .hand
    -0.08
    ediakan
    -0.08
     significativa
    -0.08
    .size
    -0.08
     mahi
    -0.07
    qdim
    -0.07
    ędzie
    -0.07
    eração
    -0.07
     madaling
    -0.07
    POSITIVE LOGITS
    님
    0.09
     Robert
    0.09
     Stephan
    0.09
     директора
    0.08
    ाध्यक्ष
    0.08
    是谁
    0.08
     Fiona
    0.08
    :innen
    0.08
     التنفيذي
    0.08
     duo
    0.08
    Activations Density 0.127%

    No Known Activations