© 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. 25042
    Prev
    Next
    INDEX
    Explanations

    <|message|>

    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
    â
    -0.09
     […]↵↵
    -0.08
    uita
    -0.08
    outil
    -0.08
     Vall
    -0.07
     provisions
    -0.07
    acios
    -0.07
     Ba
    -0.07
    vectors
    -0.07
    uit
    -0.07
    POSITIVE LOGITS
     niem
    0.09
     sml
    0.09
     akad
    0.08
     uning
    0.08
    	or
    0.08
     me
    0.07
     najm
    0.07
     maf
    0.07
    	sm
    0.07
    ...]
    0.07
    Activations Density 0.097%

    No Known Activations