© 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. 11-RESID-POST-AA
    11. 29311
    Prev
    Next
    INDEX
    Explanations

    now

    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
     deste
    -0.09
     hi
    -0.08
     outperform
    -0.07
     avant
    -0.07
     ની
    -0.07
     puis
    -0.07
     pemas
    -0.07
     rehe
    -0.07
    Formatted
    -0.07
     issu
    -0.07
    POSITIVE LOGITS
     Mö
    0.09
    ighi
    0.08
    �
    0.08
    看看
    0.08
    根据
    0.08
     recall
    0.08
    calling
    0.08
     importantly
    0.08
    由于
    0.07
    到了
    0.07
    Activations Density 0.026%

    No Known Activations