© 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. 19-RESID-POST-AA
    11. 102778
    Prev
    Next
    INDEX
    Explanations

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moesten
    -0.09
     רוצים
    -0.09
    -to
    -0.09
     concerts
    -0.08
     وذلك
    -0.08
    /routes
    -0.08
    /st
    -0.08
    /manage
    -0.08
     moeten
    -0.08
    /use
    -0.08
    POSITIVE LOGITS
     улы
    0.10
     weary
    0.09
    安心
    0.09
     solemn
    0.09
     улыб
    0.09
    ：“
    0.09
     словно
    0.08
    说道
    0.08
     demeanor
    0.08
     sonrisa
    0.08
    Activations Density 0.081%

    No Known Activations