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. 111742
    Prev
    Next
    INDEX
    Explanations

    then, commas

    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
    avance
    -0.09
    @(
    -0.08
     vict
    -0.07
     merk
    -0.07
     beve
    -0.07
     Revolutionary
    -0.07
    =this
    -0.07
    phinx
    -0.07
    sessions
    -0.07
    これは
    -0.07
    POSITIVE LOGITS
    寻找
    0.08
    电话号码
    0.07
    hala
    0.07
     potency
    0.07
     Lukas
    0.07
    Roster
    0.07
     LAP
    0.07
    找到
    0.07
     Vl
    0.07
     PRICE
    0.07
    Activations Density 0.074%

    No Known Activations