Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54289
    Prev
    Next
    INDEX
    Explanations

    service

    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
    spur
    -0.09
    deliver
    -0.08
    Measured
    -0.08
     Eclipse
    -0.08
     Nato
    -0.08
     impreg
    -0.08
    ORM
    -0.07
     ORM
    -0.07
     assumption
    -0.07
     Delivered
    -0.07
    POSITIVE LOGITS
    客服电话
    0.10
    客服
    0.10
     atendimento
    0.09
     waiting
    0.09
     patiently
    0.09
    中心官网
    0.09
    客服联系
    0.09
     wenden
    0.09
    letics
    0.09
    _help
    0.09
    Activations Density 0.033%

    No Known Activations