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. 58596
    Prev
    Next
    INDEX
    Explanations

    debit

    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
     nghỉ
    -0.08
    -worthy
    -0.08
     enclosing
    -0.08
     suprem
    -0.08
     taboo
    -0.07
     Trit
    -0.07
     sacara
    -0.07
     Pew
    -0.07
     rett
    -0.07
     defamatory
    -0.07
    POSITIVE LOGITS
     Mateo
    0.09
    Devices
    0.08
    bundle
    0.08
     immediately
    0.08
    Bundle
    0.07
    DES
    0.07
    0.07
    ฐาน
    0.07
    uchos
    0.07
     Shoes
    0.07
    Activations Density 0.002%

    No Known Activations