Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 12987
    Prev
    Next
    INDEX
    Explanations

    -

    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
     cré
    -0.08
    .gz
    -0.08
     honing
    -0.08
     стру
    -0.08
    ใจ
    -0.07
    ※
    -0.07
    -await
    -0.07
    listed
    -0.07
     abl
    -0.07
     penned
    -0.07
    POSITIVE LOGITS
     Maker
    0.08
     Examine
    0.08
     Starting
    0.08
     operation
    0.07
     Begin
    0.07
    Operation
    0.07
     اینکه
    0.07
     установить
    0.07
     Locate
    0.07
     Maxim
    0.07
    Activations Density 0.028%

    No Known Activations