© 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. 63611
    Prev
    Next
    INDEX
    Explanations

    programming

    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
     stun
    -0.09
     theft
    -0.09
     stolen
    -0.09
     lieben
    -0.08
     teuer
    -0.08
     запах
    -0.08
     bloom
    -0.08
     tros
    -0.08
    נו
    -0.08
     Nahrung
    -0.08
    POSITIVE LOGITS
     instalação
    0.08
     项
    0.08
    .empty
    0.08
     beginners
    0.08
     만들
    0.08
     बनाने
    0.08
     프로젝트
    0.08
    습
    0.08
     vazio
    0.08
     familiarize
    0.08
    Activations Density 0.011%

    No Known Activations