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. 11742
    Prev
    Next
    INDEX
    Explanations

    Punctuation and "and"

    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
     阿
    -0.08
    mol
    -0.08
    milk
    -0.07
     밝�
    -0.07
    eri
    -0.07
     அவ
    -0.07
     �
    -0.07
    Arquivo
    -0.07
    rë
    -0.07
    lx
    -0.07
    POSITIVE LOGITS
    ,也是
    0.10
    ,是
    0.10
    ,用
    0.09
     doeleinden
    0.09
     getragen
    0.08
    也是
    0.08
    ,被
    0.08
    .Stock
    0.08
    urrent
    0.08
    股票
    0.07
    Activations Density 0.221%

    No Known Activations