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. 98556
    Prev
    Next
    INDEX
    Explanations

    drain

    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
    ibbon
    -0.09
     hardcover
    -0.08
    精彩
    -0.08
    acheter
    -0.08
     Acheter
    -0.08
    -0.08
     kissed
    -0.07
     purchasing
    -0.07
     tapestry
    -0.07
     ISBN
    -0.07
    POSITIVE LOGITS
     drainage
    0.36
     drain
    0.35
     drains
    0.33
     draining
    0.33
     Drain
    0.32
    Drain
    0.31
     drained
    0.29
    -dr
    0.25
     dren
    0.22
    	dr
    0.22
    Activations Density 0.044%

    No Known Activations