© 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. 11-RESID-POST-AA
    11. 95208
    Prev
    Next
    INDEX
    Explanations

    Order-to-Cash business processes

    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
     ट्विटर
    -0.10
     creepy
    -0.09
     bcrypt
    -0.08
     Polize
    -0.08
     assust
    -0.08
     Haar
    -0.08
    بوب
    -0.08
     alcalde
    -0.08
     போலீ
    -0.08
     పోలీసులు
    -0.08
    POSITIVE LOGITS
     customers
    0.15
    客户
    0.15
     ગ્રાહ
    0.14
     customer
    0.14
     kunder
    0.14
     ग्राह
    0.13
     ग्राहक
    0.13
    客様
    0.13
    (customer
    0.13
     müşter
    0.13
    Activations Density 0.027%

    No Known Activations