© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 54840
    Prev
    Next
    INDEX
    Explanations

    _processed

    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
    Certificates
    -0.09
    Usb
    -0.08
    _ioctl
    -0.08
     Patriot
    -0.08
    (ERROR
    -0.08
     alegria
    -0.08
    _usb
    -0.08
    Addresses
    -0.08
     CERT
    -0.08
    Ratings
    -0.08
    POSITIVE LOGITS
     nltk
    0.11
     vocab
    0.11
     tokenize
    0.11
     preprocessing
    0.10
     tokenizer
    0.10
     grams
    0.09
    stemming
    0.09
    .words
    0.09
    词
    0.09
     lowercase
    0.09
    Activations Density 0.004%

    No Known Activations