© 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. 23-RESID-POST-AA
    11. 97874
    Prev
    Next
    INDEX
    Explanations

    say energy

    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
     پولیس
    -0.09
     xeeb
    -0.08
     barber
    -0.08
     гүл
    -0.07
     knji
    -0.07
     florist
    -0.07
     Floral
    -0.07
     buc
    -0.07
    鼻
    -0.07
     꽃
    -0.07
    POSITIVE LOGITS
     energy
    0.81
     Energy
    0.74
    Energy
    0.74
    energy
    0.74
    _energy
    0.73
     enerji
    0.72
     ऊर्जा
    0.72
     energía
    0.70
    能源
    0.68
     énergie
    0.67
    Activations Density 0.250%

    No Known Activations