© 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. 51346
    Prev
    Next
    INDEX
    Explanations

    PKCS12 keystore files

    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
     দ্বিত
    -0.07
     共
    -0.07
     Tesla
    -0.07
    -0.07
    έρα
    -0.07
     Tart
    -0.07
    	next
    -0.07
    	root
    -0.07
     δεύτε
    -0.07
    omit
    -0.07
    POSITIVE LOGITS
    Absolute
    0.09
     goose
    0.08
     फर्क
    0.08
    єм
    0.08
    LOAT
    0.08
     absolute
    0.08
     inseg
    0.08
    _absolute
    0.08
    viert
    0.08
    ambique
    0.08
    Activations Density 0.003%
    No Known Activations