© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 110094
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    Negative Logits
     ire
    -0.08
    �
    -0.08
     Tochter
    -0.08
     kür
    -0.08
     الأحداث
    -0.08
    객
    -0.08
     Cay
    -0.08
     اتجاه
    -0.08
     الجهات
    -0.07
    첫
    -0.07
    POSITIVE LOGITS
     parameters
    0.11
    参数
    0.10
    _params
    0.09
     parametros
    0.09
    Weights
    0.09
    _parameters
    0.09
    parameters
    0.08
    (weights
    0.08
    (Parameter
    0.08
    Parameters
    0.08
    Activations Density 0.005%

    No Known Activations