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. 60765
    Prev
    Next
    INDEX
    Explanations

    data migration to new hardware

    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
    _DIRECTION
    -0.09
    ము
    -0.08
     bravery
    -0.08
     चौ
    -0.08
     débat
    -0.08
    括
    -0.08
     कविता
    -0.08
     poeta
    -0.08
    ULSE
    -0.08
     poem
    -0.07
    POSITIVE LOGITS
     recreated
    0.12
     reinstall
    0.10
    istol
    0.09
    .sql
    0.09
     migrated
    0.09
     Copy
    0.09
     deleted
    0.09
    Copy
    0.09
    SQLite
    0.09
     recreate
    0.09
    Activations Density 0.015%

    No Known Activations