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. 130751
    Prev
    Next
    INDEX
    Explanations

    set

    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
     ดัง
    -0.10
    оты
    -0.09
    оте
    -0.09
     sain
    -0.09
    .Name
    -0.08
    .identifier
    -0.08
    .variables
    -0.08
     сначала
    -0.08
     heroine
    -0.08
    .name
    -0.08
    POSITIVE LOGITS
    minus
    0.11
     R
    0.10
    14
    0.10
     m
    0.09
     minus
    0.09
     B
    0.08
     brace
    0.08
     W
    0.08
     K
    0.08
    13
    0.08
    Activations Density 0.034%

    No Known Activations