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. 43194
    Prev
    Next
    INDEX
    Explanations

    'll

    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
     belongings
    -0.08
     diligence
    -0.07
    忍
    -0.07
    eligible
    -0.07
     etwa
    -0.07
    liefer
    -0.07
     willkommen
    -0.07
     могут
    -0.07
     birthday
    -0.07
    909
    -0.07
    POSITIVE LOGITS
     briefly
    0.08
     mencionar
    0.08
     discuss
    0.08
     ಉದ
    0.08
     Stat
    0.08
     voorbeelden
    0.08
    acağız
    0.08
     지난
    0.08
     Develop
    0.07
     Explain
    0.07
    Activations Density 0.025%

    No Known Activations