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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103527
    Prev
    Next
    INDEX
    Explanations

    Calculating principal and interest

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ರಸ್ತೆ
    -0.09
    道路
    -0.08
     irq
    -0.08
    stdin
    -0.08
    摄影
    -0.08
     SHIFT
    -0.08
     ರಸ್ತ
    -0.08
    遮
    -0.08
    歌词
    -0.08
    _toggle
    -0.08
    POSITIVE LOGITS
     accrued
    0.15
     repay
    0.14
     repayment
    0.14
     accumulated
    0.14
     matured
    0.14
     evolved
    0.14
     acumul
    0.14
     crecimiento
    0.14
     sonunda
    0.13
     monto
    0.13
    Activations Density 0.023%

    No Known Activations