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. 77130
    Prev
    Next
    INDEX
    Explanations

    amount

    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
    jego
    -0.08
    -0.08
     Rag
    -0.07
    atomic
    -0.07
     fol
    -0.07
    wu
    -0.07
     perdi
    -0.07
     destr
    -0.07
     Dug
    -0.07
     sev
    -0.07
    POSITIVE LOGITS
    是多少
    0.08
    .Amount
    0.08
     tin
    0.08
     perl
    0.08
    cake
    0.08
     apparel
    0.08
    .amount
    0.08
     మంది
    0.07
     viene
    0.07
     vem
    0.07
    Activations Density 0.032%

    No Known Activations