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. 98626
    Prev
    Next
    INDEX
    Explanations

    )

    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
     pagsus
    -0.09
    compression
    -0.08
     Through
    -0.08
    seal
    -0.08
     Schmuck
    -0.08
     surn
    -0.08
    zaam
    -0.08
    突破
    -0.07
    through
    -0.07
     swingers
    -0.07
    POSITIVE LOGITS
     khỏi
    0.15
     subtract
    0.14
    Subtract
    0.13
     minu
    0.13
    (remove
    0.11
     off
    0.11
     leaving
    0.11
     twice
    0.11
    /add
    0.11
    との差
    0.11
    Activations Density 0.053%

    No Known Activations