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. 106168
    Prev
    Next
    INDEX
    Explanations

    sign

    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
    fog
    -0.08
     fog
    -0.07
     insurance
    -0.07
     стресс
    -0.07
    \data
    -0.07
    mediatamente
    -0.07
     персон
    -0.07
     हॉ
    -0.07
     хат
    -0.07
     publ
    -0.07
    POSITIVE LOGITS
     Depends
    0.10
    depends
    0.10
     depending
    0.09
    是否
    0.09
     зависит
    0.09
    真假
    0.09
    判断
    0.09
    depending
    0.09
     divis
    0.08
     dependiendo
    0.08
    Activations Density 0.014%

    No Known Activations