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. 43173
    Prev
    Next
    INDEX
    Explanations

    pillows

    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
     atrop
    -0.08
     சென்ற
    -0.08
     implicitly
    -0.07
     prerequisite
    -0.07
     Nieder
    -0.07
     stack
    -0.07
    Carbon
    -0.07
     immersive
    -0.07
    nano
    -0.07
     vertically
    -0.07
    POSITIVE LOGITS
     жак
    0.09
     Thema
    0.09
     dekor
    0.08
     декоратив
    0.08
     thema
    0.08
     theatrical
    0.08
     theater
    0.08
     ചേര്
    0.08
     refurbishment
    0.08
     Ogun
    0.08
    Activations Density 0.004%

    No Known Activations