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. 61300
    Prev
    Next
    INDEX
    Explanations

    Get

    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
     diper
    -0.08
     miz
    -0.08
     estet
    -0.08
    automat
    -0.08
    home
    -0.08
     artık
    -0.07
    .home
    -0.07
     architect
    -0.07
     iso
    -0.07
    esthetic
    -0.07
    POSITIVE LOGITS
    .populate
    0.12
    Populate
    0.10
     werking
    0.08
     INTO
    0.08
    /constants
    0.08
    inda
    0.08
     snprintf
    0.08
     \↵
    0.08
    CHKERRQ
    0.08
     determine
    0.08
    Activations Density 0.006%

    No Known Activations