© 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. 71194
    Prev
    Next
    INDEX
    Explanations

    art and painting

    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
     shutting
    -0.10
     shutdown
    -0.09
     pensions
    -0.09
    领取
    -0.09
    -login
    -0.09
    -training
    -0.09
    培训
    -0.09
    給与
    -0.09
    -confirm
    -0.09
     internships
    -0.09
    POSITIVE LOGITS
     эстет
    0.13
     evoc
    0.12
     evoke
    0.12
     storytelling
    0.12
     компози
    0.11
     aesthetics
    0.11
     ప్రేక్షక
    0.11
     storyt
    0.11
     aesthetic
    0.11
     musical
    0.11
    Activations Density 0.068%

    No Known Activations