© 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. 54496
    Prev
    Next
    INDEX
    Explanations

    svg code

    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
    	callback
    -0.08
    当地
    -0.07
     prohib
    -0.07
     exponentially
    -0.07
    	param
    -0.07
    IFORM
    -0.07
     protég
    -0.07
    פחה
    -0.07
     eval
    -0.07
    	local
    -0.07
    POSITIVE LOGITS
     allergens
    0.09
    狸
    0.08
     attent
    0.08
    passwd
    0.08
     Password
    0.08
     allergies
    0.08
     বৃ
    0.08
     allerg
    0.08
     attenzione
    0.08
     Allerg
    0.08
    Activations Density 0.024%

    No Known Activations