© 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. 23-RESID-POST-AA
    11. 49640
    Prev
    Next
    INDEX
    Explanations

    bases

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tensions
    -0.09
     wing
    -0.09
     Cable
    -0.09
    Cable
    -0.08
     câble
    -0.08
    шел
    -0.08
     cursor
    -0.08
    (edge
    -0.08
     kout
    -0.08
     Cursor
    -0.08
    POSITIVE LOGITS
     bases
    0.28
    bases
    0.24
     Bases
    0.24
    Bases
    0.23
     базы
    0.16
     basi
    0.16
    BASE
    0.15
    Base
    0.15
     BASE
    0.15
     बेस
    0.15
    Activations Density 0.050%

    No Known Activations