© 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. 111082
    Prev
    Next
    INDEX
    Explanations

    Brevity and clarity

    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
     대한
    -0.08
     Dunia
    -0.07
     Meadows
    -0.07
     TSA
    -0.07
    /her
    -0.07
     determinant
    -0.07
     Ger
    -0.07
     conhecer
    -0.07
     ג
    -0.07
     따르면
    -0.07
    POSITIVE LOGITS
    潔
    0.10
     exces
    0.09
    Vest
    0.09
    reu
    0.09
     excessive
    0.09
     brev
    0.09
    Length
    0.09
    主义
    0.09
    Whitespace
    0.09
     courte
    0.08
    Activations Density 0.036%

    No Known Activations