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. 30649
    Prev
    Next
    INDEX
    Explanations

    adoption

    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
     robbed
    -0.08
     entfernen
    -0.08
    -'
    -0.08
     rédaction
    -0.08
     shuffle
    -0.07
     perder
    -0.07
     included
    -0.07
    ½
    -0.07
    -0.07
     Be
    -0.07
    POSITIVE LOGITS
     Adoption
    0.13
     uptake
    0.13
     अपन
    0.12
    推广
    0.12
     adoption
    0.12
     Upt
    0.11
     widespread
    0.11
     확대
    0.10
     mainstream
    0.10
     enthusiast
    0.10
    Activations Density 0.094%

    No Known Activations