© 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. 11-RESID-POST-AA
    11. 54597
    Prev
    Next
    INDEX
    Explanations

    zero vector

    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
     sosial
    -0.08
     producteurs
    -0.08
    Зак
    -0.08
     ROUND
    -0.08
     sociales
    -0.08
     rounds
    -0.07
     Raw
    -0.07
    ices
    -0.07
     Round
    -0.07
     Зак
    -0.07
    POSITIVE LOGITS
    /null
    0.08
    	k
    0.08
    (Auth
    0.08
     ʻole
    0.08
    /non
    0.08
    netje
    0.08
     entfernen
    0.08
    	endif
    0.07
    ictionary
    0.07
    っ
    0.07
    Activations Density 0.011%

    No Known Activations