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. 11-RESID-POST-AA
    6. 12990
    Prev
    Next
    INDEX
    Explanations

    hashing and code

    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
     maternity
    -0.08
     valign
    -0.08
    Starter
    -0.08
     staffing
    -0.08
    Staff
    -0.08
    quipment
    -0.08
     Staffing
    -0.07
    Lady
    -0.07
     listed
    -0.07
     unde
    -0.07
    POSITIVE LOGITS
     hashing
    0.14
    	hash
    0.13
     hashes
    0.13
     checksum
    0.12
    hash
    0.12
     hash
    0.12
    .hash
    0.11
     hashed
    0.11
     encode
    0.11
    _HASH
    0.11
    Activations Density 0.011%

    No Known Activations