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. 23-RESID-POST-AA
    6. 130978
    Prev
    Next
    INDEX
    Explanations

    oil

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TSV
    -0.10
     SNC
    -0.09
     Battalion
    -0.09
     Hermione
    -0.09
     Ramsey
    -0.09
     Bahn
    -0.08
     ferrovi
    -0.08
    Json
    -0.08
    _UART
    -0.08
    公安
    -0.08
    POSITIVE LOGITS
     oil
    0.49
     तेल
    0.44
    油
    0.43
     Oil
    0.43
     olie
    0.43
     oils
    0.42
     óleo
    0.41
    Oil
    0.41
     huile
    0.40
     minyak
    0.38
    Activations Density 0.136%

    No Known Activations