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. 75946
    Prev
    Next
    INDEX
    Explanations

    mx

    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
    社
    -0.09
    .ORDER
    -0.08
     Johnny
    -0.07
    Inet
    -0.07
     Libert
    -0.07
    物流
    -0.07
     liberté
    -0.07
     delito
    -0.07
    .Workflow
    -0.07
     SOCIAL
    -0.07
    POSITIVE LOGITS
     basin
    0.09
     resized
    0.08
     enlarged
    0.08
     allocated
    0.08
     最大
    0.08
     Basin
    0.08
     blasts
    0.08
     allotted
    0.08
     largest
    0.08
    Largest
    0.08
    Activations Density 0.002%

    No Known Activations