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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 96947
    Prev
    Next
    INDEX
    Explanations

    Fees

    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
     manufactured
    -0.09
     pelvis
    -0.09
     manne
    -0.08
     Deploy
    -0.08
     mannequin
    -0.08
     umat
    -0.08
     ব
    -0.08
     stitched
    -0.07
     Пал
    -0.07
    Studio
    -0.07
    POSITIVE LOGITS
     fees
    0.25
    fees
    0.21
    Fees
    0.21
     Fees
    0.21
    手续费
    0.20
     costs
    0.19
     फीस
    0.19
     Gebühren
    0.19
     taxes
    0.19
     комиссии
    0.19
    Activations Density 0.029%

    No Known Activations