© 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. 79209
    Prev
    Next
    INDEX
    Explanations

    publications

    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
    ās
    -0.08
    Continu
    -0.08
     accumulate
    -0.08
     หม
    -0.08
     telephone
    -0.08
     continu
    -0.08
     retorn
    -0.08
     haine
    -0.08
    續
    -0.08
     décro
    -0.07
    POSITIVE LOGITS
    发表于
    0.12
     announced
    0.10
    公布
    0.10
    发布
    0.10
    论文
    0.10
     ಪ್ರಕಟ
    0.10
     publication
    0.10
     Veröffentlichung
    0.10
    刊
    0.10
     published
    0.10
    Activations Density 0.028%

    No Known Activations