© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110835
    Prev
    Next
    INDEX
    Explanations

    interest calculations

    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
     Cuisine
    -0.09
     Kinect
    -0.09
     palette
    -0.09
     Squad
    -0.08
     mouse
    -0.08
    mouse
    -0.08
     Interface
    -0.08
    _spawn
    -0.08
     selfies
    -0.08
     Spawn
    -0.08
    POSITIVE LOGITS
    金额
    0.15
     টাকা
    0.13
     مبلغ
    0.13
    本金
    0.12
    贷
    0.12
     depreciation
    0.12
     रकम
    0.12
     prepaid
    0.12
     savings
    0.11
     taxable
    0.11
    Activations Density 0.031%

    No Known Activations