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. 30567
    Prev
    Next
    INDEX
    Explanations

    0

    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
     deny
    -0.08
     compt
    -0.08
    /sql
    -0.07
    ناق
    -0.07
    invalidate
    -0.07
    arst
    -0.07
     marshal
    -0.07
     fuzz
    -0.07
    /projects
    -0.07
    /models
    -0.07
    POSITIVE LOGITS
    532
    0.08
    028
    0.08
    Idx
    0.08
     spirited
    0.07
     Goods
    0.07
    038
    0.07
    简称
    0.07
    gele
    0.07
    வை
    0.07
    ename
    0.07
    Activations Density 0.002%

    No Known Activations