© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 45741
    Prev
    Next
    INDEX
    Explanations

    numerical calculations

    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
    қай
    -0.08
     تق
    -0.07
     Bolsa
    -0.07
     shredd
    -0.07
     afl
    -0.07
     ges
    -0.07
     desg
    -0.07
    ्क
    -0.07
    Cast
    -0.07
    मै
    -0.07
    POSITIVE LOGITS
     PES
    0.08
     liters
    0.08
    _INIT
    0.08
     prehistoric
    0.07
     picnic
    0.07
    akker
    0.07
     Sod
    0.07
     Hin
    0.07
     trat
    0.07
    Ѕ
    0.07
    Activations Density 0.040%

    No Known Activations