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. 111805
    Prev
    Next
    INDEX
    Explanations

    adhere

    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
     đời
    -0.08
     ym
    -0.07
     inox
    -0.07
    setz
    -0.07
     המת
    -0.07
    ümüzde
    -0.07
    odable
    -0.07
    ays
    -0.07
     يحتاج
    -0.07
     Employ
    -0.07
    POSITIVE LOGITS
     envers
    0.09
    以下
    0.08
    ിട്ട്
    0.08
    回复
    0.08
     kapit
    0.08
    遵
    0.08
     regarding
    0.08
    回答
    0.07
     adhere
    0.07
     prins
    0.07
    Activations Density 0.003%

    No Known Activations