© 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. 44651
    Prev
    Next
    INDEX
    Explanations

    Numbers ending in 000

    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
    	control
    -0.08
    estion
    -0.08
    азақстан
    -0.08
    ిశ
    -0.08
     parlement
    -0.08
     বলা
    -0.08
     Parlamento
    -0.08
    ikino
    -0.08
     считается
    -0.08
     Contrary
    -0.08
    POSITIVE LOGITS
    พื้น
    0.08
     removable
    0.08
    0.08
     раз
    0.07
    สะ
    0.07
     plugged
    0.07
    ragen
    0.07
     hue
    0.07
     spaced
    0.07
     Sw
    0.07
    Activations Density 0.042%

    No Known Activations