© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 95893
    Prev
    Next
    INDEX
    Explanations

    TCP window

    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
     minced
    -0.08
    .Replace
    -0.08
     recopil
    -0.08
     root
    -0.07
    集
    -0.07
    _root
    -0.07
     moul
    -0.07
     compil
    -0.07
     mundane
    -0.07
    ,再
    -0.07
    POSITIVE LOGITS
     negotiation
    0.09
     നിയന്ത്ര
    0.09
     avanço
    0.09
     reciproc
    0.09
    Negoti
    0.09
    capacity
    0.09
     negotiations
    0.08
     ظرفیت
    0.08
    advance
    0.08
    	progress
    0.08
    Activations Density 0.002%

    No Known Activations