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. 58605
    Prev
    Next
    INDEX
    Explanations

    alignment

    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
     규모
    -0.08
     discounted
    -0.08
     heed
    -0.08
    تے
    -0.08
     hypnosis
    -0.08
    cule
    -0.08
     Reid
    -0.07
    耗
    -0.07
    毒
    -0.07
    .Record
    -0.07
    POSITIVE LOGITS
     valign
    0.13
     Alignment
    0.13
    -align
    0.13
     alignment
    0.12
    :left
    0.12
    :center
    0.12
    .Alignment
    0.12
    Alignment
    0.11
    alignment
    0.11
    =center
    0.11
    Activations Density 0.006%

    No Known Activations