Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 106217
    Prev
    Next
    INDEX
    Explanations

    concurrent

    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
     affiche
    -0.08
     ld
    -0.08
    监
    -0.08
     hə
    -0.08
     심
    -0.08
    .monitor
    -0.08
     ماه
    -0.07
     neun
    -0.07
     inclusief
    -0.07
     ulang
    -0.07
    POSITIVE LOGITS
    ંભ
    0.08
     foyer
    0.08
     каким
    0.08
     રીતે
    0.08
     સર્જ
    0.08
    684
    0.08
     reizen
    0.08
     shaving
    0.08
     countertop
    0.08
     સમયે
    0.08
    Activations Density 0.003%

    No Known Activations