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. 111914
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ыр
    -0.07
     सौ
    -0.07
     പത
    -0.07
     sij
    -0.07
    -return
    -0.07
    subs
    -0.07
    MLE
    -0.07
     जु
    -0.07
    contra
    -0.07
     aflevering
    -0.07
    POSITIVE LOGITS
     besch
    0.10
     দিয়ে
    0.09
     মাঝে
    0.08
    śród
    0.08
     surrounded
    0.08
     turmoil
    0.08
     Tril
    0.08
     محور
    0.08
     toho
    0.08
     obnox
    0.08
    Activations Density 0.016%

    No Known Activations