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. 7-RESID-POST-AA
    6. 130994
    Prev
    Next
    INDEX
    Explanations

    Encryption protocols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Delf
    -0.08
    ạnh
    -0.08
     Bitcoin
    -0.07
    chnitten
    -0.07
    «
    -0.07
     ters
    -0.07
    adata
    -0.07
     «
    -0.07
     дап
    -0.07
    Yak
    -0.07
    POSITIVE LOGITS
     pioneer
    0.09
    .coll
    0.08
     pilot
    0.07
     displays
    0.07
    _effect
    0.07
     attempted
    0.07
     granted
    0.07
     monday
    0.07
    .display
    0.07
     boolean
    0.07
    Activations Density 0.001%

    No Known Activations