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. 58644
    Prev
    Next
    INDEX
    Explanations

    edge

    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
     jit
    -0.08
     zal
    -0.08
     tête
    -0.08
     Owen
    -0.08
     concurrence
    -0.08
     jitter
    -0.08
     rolls
    -0.08
     hopper
    -0.07
     marg
    -0.07
     قائ
    -0.07
    POSITIVE LOGITS
     isa
    0.08
    LG
    0.08
    Reliable
    0.08
     exhausting
    0.07
    Reli
    0.07
    540
    0.07
    -icons
    0.07
    Sight
    0.07
    "The
    0.07
     whitespace
    0.07
    Activations Density 0.004%

    No Known Activations