© 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. 79452
    Prev
    Next
    INDEX
    Explanations

    reference lists

    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
     chocolate
    -0.08
    okol
    -0.08
     succinct
    -0.07
     adjectives
    -0.07
     asunto
    -0.07
     Hob
    -0.07
     afbeelding
    -0.07
     dx
    -0.07
     byt
    -0.07
     joystick
    -0.07
    POSITIVE LOGITS
    original
    0.08
    .original
    0.08
    	else
    0.08
    олго
    0.08
    거
    0.08
     ต
    0.08
     original
    0.08
     داخل
    0.08
     else's
    0.08
     originales
    0.08
    Activations Density 0.008%

    No Known Activations