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. 65419
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     ос
    -0.07
     vida
    -0.07
    анная
    -0.07
    -0.07
     playa
    -0.07
     semakin
    -0.07
     advancement
    -0.07
    avat
    -0.07
     playground
    -0.07
     בנושא
    -0.07
    POSITIVE LOGITS
    独
    0.09
    原创
    0.09
     독
    0.09
     độc
    0.08
    自产
    0.08
     nguyên
    0.08
    非
    0.08
    なので
    0.08
    erian
    0.08
    沒有
    0.08
    Activations Density 0.095%

    No Known Activations