Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 416
    Prev
    Next
    INDEX
    Explanations

    suffixes "ity" and "ism"

    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
     vantage
    -0.08
     �
    -0.08
     convincing
    -0.07
     Arithmetic
    -0.07
     ribs
    -0.07
     chill
    -0.07
    black
    -0.07
     আর
    -0.07
     طل
    -0.07
     സാഹചര
    -0.07
    POSITIVE LOGITS
     cid
    0.08
     conspiracy
    0.07
     mellitus
    0.07
     �
    0.07
    던
    0.07
    gig
    0.07
     Ame
    0.07
    iód
    0.07
    .'↵↵
    0.07
     alas
    0.07
    Activations Density 0.174%

    No Known Activations