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. 113057
    Prev
    Next
    INDEX
    Explanations

    one

    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
    ARY
    -0.08
    ILLI
    -0.08
     Exerc
    -0.08
    -0.08
     chirurgie
    -0.07
    AGR
    -0.07
    문의
    -0.07
    emor
    -0.07
    ary
    -0.07
    ARIO
    -0.07
    POSITIVE LOGITS
     આવે
    0.09
    々
    0.08
    zam
    0.08
    િત
    0.08
    ગ
    0.08
    ोस
    0.08
    त्या
    0.08
     move
    0.08
    ट
    0.07
    kish
    0.07
    Activations Density 0.002%

    No Known Activations