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. 60868
    Prev
    Next
    INDEX
    Explanations

    resolution

    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
     unterschied
    -0.08
     erbjud
    -0.08
     inseg
    -0.07
    ათვის
    -0.07
     ọja
    -0.07
     Slight
    -0.07
     njengoba
    -0.07
    subpackage
    -0.07
     ibeere
    -0.07
     idiyele
    -0.07
    POSITIVE LOGITS
     decree
    0.12
     بشأن
    0.10
    决定
    0.10
    批准
    0.09
     关于
    0.09
     صادر
    0.09
     �
    0.09
    宣布
    0.09
     unanimously
    0.09
    tee
    0.09
    Activations Density 0.037%

    No Known Activations