© 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. 23-RESID-POST-AA
    11. 50755
    Prev
    Next
    INDEX
    Explanations

    base64 encoding

    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
     cadas
    -0.08
    anthem
    -0.08
    Nationality
    -0.08
     nacionales
    -0.08
    usic
    -0.08
    conciliation
    -0.08
     tragedy
    -0.08
     desktops
    -0.08
     superficies
    -0.08
     national
    -0.08
    POSITIVE LOGITS
     Base
    0.34
    Base
    0.30
     base
    0.29
    _base
    0.28
    	Base
    0.28
    .Base
    0.26
    (Base
    0.26
     BASE
    0.25
    	base
    0.25
    _Base
    0.25
    Activations Density 0.012%

    No Known Activations