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. 12867
    Prev
    Next
    INDEX
    Explanations

    as

    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
     asian
    -0.08
     Obviously
    -0.08
     airway
    -0.08
     difíciles
    -0.08
     fireplaces
    -0.08
     fireplace
    -0.07
     lil
    -0.07
     persp
    -0.07
     Bulgarian
    -0.07
    וה
    -0.07
    POSITIVE LOGITS
     �
    0.07
     supérieure
    0.07
    É
    0.07
     organização
    0.07
     Thames
    0.07
     avali
    0.07
    램
    0.07
     �
    0.06
    une
    0.06
    /TR
    0.06
    Activations Density 0.499%

    No Known Activations