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. 112437
    Prev
    Next
    INDEX
    Explanations

    cost effectiveness

    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
     wool
    -0.07
     comp
    -0.07
     mã
    -0.07
     clang
    -0.07
    预
    -0.07
     leh
    -0.07
     many
    -0.07
     feel
    -0.07
     public
    -0.07
     ਤ
    -0.07
    POSITIVE LOGITS
    XB
    0.09
     XB
    0.09
    ერ�
    0.09
     resurrection
    0.09
     soulmate
    0.09
     gestart
    0.09
    начала
    0.09
     spontan
    0.09
     holy
    0.09
     ಸಾಹ
    0.09
    Activations Density 0.002%

    No Known Activations