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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 77412
    Prev
    Next
    INDEX
    Explanations

    API proxy and security

    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
    _float
    -0.08
     float
    -0.08
    körper
    -0.08
    ,float
    -0.07
    _struct
    -0.07
     Float
    -0.07
     mindset
    -0.07
    _insert
    -0.07
     Bailey
    -0.07
     elektrische
    -0.07
    POSITIVE LOGITS
    _PROXY
    0.10
    არ
    0.10
     bridges
    0.09
     lula
    0.09
     отече
    0.09
     proxies
    0.09
    服务器
    0.09
     intermedi
    0.08
    ოლო
    0.08
    JS
    0.08
    Activations Density 0.007%

    No Known Activations