© 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 EvalsExportsinterp-engineNEWAPI 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. 70578
    Prev
    Next
    INDEX
    Explanations

    questioning statements/implications

    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
     Hef
    -0.08
     aliado
    -0.07
    /to
    -0.07
    [],
    -0.07
     hagati
    -0.07
     diligent
    -0.07
    emos
    -0.07
     middle
    -0.07
     full
    -0.07
    śred
    -0.07
    POSITIVE LOGITS
    违反
    0.13
     unrealistic
    0.12
    unlikely
    0.11
     bizarre
    0.11
     weird
    0.11
    违
    0.11
     unnatural
    0.10
     unusual
    0.10
     strangely
    0.10
     unbelievably
    0.10
    Activations Density 0.073%

    No Known Activations