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. 112293
    Prev
    Next
    INDEX
    Explanations

    the

    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
    集
    -0.09
     blend
    -0.08
     edition
    -0.08
     clusters
    -0.07
     surface
    -0.07
    blend
    -0.07
     cluster
    -0.07
    Blend
    -0.07
    编辑
    -0.07
     LIN
    -0.07
    POSITIVE LOGITS
     půj
    0.11
    貸
    0.11
     repayments
    0.11
     whom
    0.11
     faiz
    0.10
     টাকা
    0.10
     hypocrisy
    0.10
     مخال
    0.10
     repayment
    0.10
     lender
    0.10
    Activations Density 0.010%

    No Known Activations