© 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. 51001
    Prev
    Next
    INDEX
    Explanations

    say "items"

    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
     mobilier
    -0.10
     meubles
    -0.10
     establecimientos
    -0.10
    usc
    -0.09
    (widget
    -0.08
    (component
    -0.08
     мебели
    -0.08
     meubels
    -0.08
    ialist
    -0.08
    Identifiers
    -0.08
    POSITIVE LOGITS
     kn
    0.09
     craft
    0.09
     boîte
    0.08
    Craft
    0.08
     vidrio
    0.08
    adona
    0.08
     caja
    0.07
     cajas
    0.07
     seldom
    0.07
    _REMOTE
    0.07
    Activations Density 0.005%

    No Known Activations