© 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. 69149
    Prev
    Next
    INDEX
    Explanations

    bench

    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
    ivant
    -0.08
    Medium
    -0.07
    elem
    -0.07
    -0.07
     babel
    -0.07
     fittings
    -0.07
     elem
    -0.07
     misplaced
    -0.07
     hup
    -0.07
     contacted
    -0.07
    POSITIVE LOGITS
     namun
    0.09
    Rather
    0.08
    rook
    0.08
     tačiau
    0.08
    ਟੀ
    0.08
     Rather
    0.08
     surgir
    0.08
    ાષ્ટ્રીય
    0.08
    폰
    0.08
     televisão
    0.08
    Activations Density 0.012%
    No Known Activations