© 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 EvalsExportsAPI 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. 69240
    Prev
    Next
    INDEX
    Explanations

    Luhmann

    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
    �
    -0.08
    059
    -0.08
     presentan
    -0.08
     disliked
    -0.07
    存在
    -0.07
    始
    -0.07
    禁止
    -0.07
     dislike
    -0.07
    �
    -0.07
    ATS
    -0.07
    POSITIVE LOGITS
    SEG
    0.09
    snap
    0.08
     snap
    0.08
    vacc
    0.08
     кожу
    0.08
     Blockchain
    0.08
    .buf
    0.07
    -lib
    0.07
     кожа
    0.07
     CNBC
    0.07
    Activations Density 0.001%

    No Known Activations