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. 15-RESID-POST-AA
    6. 19136
    Prev
    Next
    INDEX
    Explanations

    Question marks

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iyo
    -0.09
     Entscheidungen
    -0.09
     nde
    -0.08
     ਅਤੇ
    -0.08
     Denver
    -0.08
    =req
    -0.08
     και
    -0.08
     și
    -0.07
     Decisions
    -0.07
     ενός
    -0.07
    POSITIVE LOGITS
     தவ
    0.09
     mistakenly
    0.09
    perhaps
    0.09
     perhaps
    0.09
     somehow
    0.08
    Perhaps
    0.08
     തെ
    0.08
     misunderstood
    0.08
     ഉറ
    0.08
    �
    0.08
    Activations Density 0.031%

    No Known Activations