Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 67921
    Prev
    Next
    INDEX
    Explanations

    period

    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
     qim
    -0.08
     rand
    -0.08
     الشكل
    -0.08
     brav
    -0.08
     gec
    -0.07
    ാടക
    -0.07
    �
    -0.07
     Aurora
    -0.07
    مالي
    -0.07
    osy
    -0.07
    POSITIVE LOGITS
     Wer
    0.08
     mid
    0.07
    주는
    0.07
     excellent
    0.07
    세요
    0.07
     Gar
    0.07
     Kurz
    0.07
     работы
    0.07
    pects
    0.07
     Kick
    0.07
    Activations Density 0.113%

    No Known Activations