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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 58926
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    不过
    -0.09
     nhất
    -0.08
     meanwhile
    -0.07
    还有
    -0.07
     bese
    -0.07
    压力
    -0.07
     deliberately
    -0.07
     Kane
    -0.07
    スト
    -0.07
    یہ
    -0.07
    POSITIVE LOGITS
     повод
    0.09
    genes
    0.08
     сумму
    0.08
     foundation
    0.08
    ғ
    0.08
     своего
    0.08
    ्द
    0.07
    gsm
    0.07
    {↵
    0.07
    zp
    0.07
    Activations Density 0.106%

    No Known Activations