Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130904
    Prev
    Next
    INDEX
    Explanations

    fairness and justice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yn
    -0.07
    			  
    -0.07
    /native
    -0.07
     cameo
    -0.07
    -CON
    -0.07
    		    	
    -0.07
     cris
    -0.07
    炸
    -0.07
    .Disable
    -0.07
     Крем
    -0.06
    POSITIVE LOGITS
    公平
    0.53
     fairness
    0.52
     fair
    0.47
     Fair
    0.46
    Fair
    0.45
    fair
    0.44
     ನ್ಯಾಯ
    0.43
     justiça
    0.40
     equitable
    0.40
     justa
    0.39
    Activations Density 0.104%

    No Known Activations