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. 49171
    Prev
    Next
    INDEX
    Explanations

    reduce

    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
     Abuja
    -0.09
    ását
    -0.08
    (">
    -0.08
    times
    -0.08
    anm
    -0.08
    Annot
    -0.08
    áció
    -0.08
    ANE
    -0.08
     कहल
    -0.08
     entstehen
    -0.08
    POSITIVE LOGITS
     حجم
    0.09
     срок
    0.08
     количества
    0.08
     wording
    0.08
     basta
    0.07
     rhythmic
    0.07
     размера
    0.07
     suffice
    0.07
     кор
    0.07
     privileges
    0.07
    Activations Density 0.014%

    No Known Activations