© 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. 984
    Prev
    Next
    INDEX
    Explanations

    Ancient Greek philosophers

    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
     EPC
    -0.09
    risis
    -0.08
     opa
    -0.08
     zor
    -0.07
    yu
    -0.07
     આગળ
    -0.07
     ',↵
    -0.07
     ï
    -0.07
    	mp
    -0.07
    üyük
    -0.07
    POSITIVE LOGITS
     dret
    0.08
     artesanal
    0.07
     натураль
    0.07
     subjekt
    0.07
     MADE
    0.07
     individuality
    0.07
     сель
    0.07
    /apache
    0.07
     posting
    0.07
     hac
    0.07
    Activations Density 0.000%

    No Known Activations