© 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. 91635
    Prev
    Next
    INDEX
    Explanations

    BERT models

    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
    .JPG
    -0.09
     bienes
    -0.09
     homeowner
    -0.09
    激情
    -0.09
    _usb
    -0.09
     germs
    -0.09
     township
    -0.09
    Usb
    -0.08
     تغي
    -0.08
     भय
    -0.08
    POSITIVE LOGITS
     pretrained
    0.13
     logits
    0.13
     NLP
    0.13
     hugging
    0.12
     tokenizer
    0.12
     embeddings
    0.12
     Hug
    0.11
     rollout
    0.11
     vocab
    0.11
    .embedding
    0.10
    Activations Density 0.026%

    No Known Activations