© 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. 26250
    Prev
    Next
    INDEX
    Explanations

    <|end|>

    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
     izv
    -0.08
     izl
    -0.08
     sportifs
    -0.08
     iz
    -0.08
     ست
    -0.08
     piz
    -0.08
     نوش
    -0.08
     Chuck
    -0.08
     eat
    -0.08
    _sup
    -0.07
    POSITIVE LOGITS
    	answer
    0.08
    答
    0.08
     meiner
    0.08
    我的
    0.08
     ನನ್ನ
    0.08
    ്യമ
    0.07
     refers
    0.07
     betrifft
    0.07
     filenames
    0.07
    	tc
    0.07
    Activations Density 0.048%

    No Known Activations