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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 77240
    Prev
    Next
    INDEX
    Explanations

    square root

    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
     Edo
    -0.09
    DCF
    -0.08
     dí
    -0.08
     rep
    -0.08
    Alchemy
    -0.07
    Mond
    -0.07
     pipelines
    -0.07
     Pip
    -0.07
     اتجاه
    -0.07
    respect
    -0.07
    POSITIVE LOGITS
     unmittelbar
    0.09
     пропис
    0.08
     بتن
    0.08
     beton
    0.08
    )throws
    0.08
     שלכם
    0.08
    ovať
    0.08
     prea
    0.08
     lau
    0.08
     لین
    0.08
    Activations Density 0.004%

    No Known Activations