SAE_DINOv3_ViT-L-16_IN1K

SAE for Meta's DINOv3 ViT-L/16 trained on ImageNet-1K Activations

• Homepage: https://osu-nlp-group.github.io/saev
• Code: https://github.com/OSU-NLP-Group/saev
• Preprint: https://arxiv.org/abs/2511.17735
• Demos: https://osu-nlp-group.github.io/saev#demos
• Point of Contact: Sam Stevens

Checkpoints

Each checkpoint is a sparse autoencoder (SAE) trained on a different layer with a different sparsity level. Pick the checkpoint that matches your target layer and desired sparsity (L0).

This metadata is also available in manifest.jsonl at the repo root for programmatic access.

Usage

from huggingface_hub import hf_hub_download

import saev.nn

path = hf_hub_download("osunlp/SAE_DINOv3_ViT-L-16_IN1K", "layer_23/9fn4l6rf/sae.pt")
sae = saev.nn.load(path)

Inference Instructions

Follow the instructions here.