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. 120357
    Prev
    Next
    INDEX
    Explanations

    disco

    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
     disturb
    -0.08
     respecting
    -0.08
    оват
    -0.08
     Oss
    -0.08
    Respect
    -0.07
    _secondary
    -0.07
    角
    -0.07
    不起
    -0.07
    imam
    -0.07
     respet
    -0.07
    POSITIVE LOGITS
    -era
    0.10
     раст
    0.09
     వీ
    0.08
     decadent
    0.08
     Rihanna
    0.08
    ทั้งหมด
    0.08
    ผลิต
    0.08
     ETF
    0.08
     industriel
    0.08
     promis
    0.08
    Activations Density 0.001%

    No Known Activations