© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-RESID-POST-AA
    11. 16342
    Prev
    Next
    INDEX
    Explanations

    removable

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     valam
    -0.08
    etine
    -0.08
     вдруг
    -0.08
    ogenesis
    -0.08
     الأمريكي
    -0.08
     unwavering
    -0.08
    ستم
    -0.08
    ృద్ధ
    -0.08
     నిజ
    -0.08
     unequiv
    -0.08
    POSITIVE LOGITS
    যোগ্য
    0.10
     detachable
    0.10
     adjustable
    0.09
     removable
    0.09
     facilement
    0.09
     recyclable
    0.09
     rechargeable
    0.09
    /re
    0.09
     reusable
    0.09
    /Add
    0.09
    Activations Density 0.013%

    No Known Activations