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. 15-RESID-POST-AA
    6. 177
    Prev
    Next
    INDEX
    Explanations

    woman

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    			 
    -0.09
    ینو
    -0.08
    			  
    -0.08
    		 
    -0.08
    ublishing
    -0.08
     wm
    -0.08
    openhagen
    -0.08
    NUMX
    -0.07
     календар
    -0.07
    	    	
    -0.07
    POSITIVE LOGITS
    ...?
    0.08
    …
    0.08
    ...
    0.08
    ושת
    0.08
    ję
    0.08
     Saga
    0.08
    ji
    0.08
    ங்க
    0.08
     dashed
    0.08
     Solomon
    0.07
    Activations Density 0.000%

    No Known Activations