© 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 EvalsExportsAPI 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. 69048
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and lists

    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
    掛
    -0.08
    ocratic
    -0.08
    Investor
    -0.08
     pensions
    -0.08
     السك
    -0.07
    ਇਆ
    -0.07
    Salary
    -0.07
    Kab
    -0.07
     Werte
    -0.07
    legte
    -0.07
    POSITIVE LOGITS
     visually
    0.13
    视觉
    0.11
     floppy
    0.11
     рисун
    0.11
     elongated
    0.10
     Figures
    0.10
    .shape
    0.10
     shapes
    0.10
     визу
    0.10
    (fig
    0.10
    Activations Density 0.016%

    No Known Activations