© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 108604
    Prev
    Next
    INDEX
    Explanations

    stratified sampling calculations

    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
    iginal
    -0.09
     sembl
    -0.08
    Seit
    -0.08
    nou
    -0.08
     Ebook
    -0.08
    figure
    -0.08
     abd
    -0.08
    ikka
    -0.08
    prefix
    -0.07
     соверш
    -0.07
    POSITIVE LOGITS
     allocations
    0.11
    allocated
    0.10
     allocation
    0.10
    Allocated
    0.10
    Allocation
    0.09
     Allocation
    0.09
     allocated
    0.09
     allocate
    0.09
    .allocate
    0.08
     allocating
    0.08
    Activations Density 0.010%

    No Known Activations