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. 15-RESID-POST-AA
    6. 18989
    Prev
    Next
    INDEX
    Explanations

    ^{

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .tb
    -0.09
     banque
    -0.08
    Thu
    -0.08
    .Shapes
    -0.08
     Герм
    -0.08
    -mm
    -0.08
    /mm
    -0.08
     proposing
    -0.08
    /XML
    -0.08
     MMM
    -0.08
    POSITIVE LOGITS
     soy
    0.08
     poke
    0.08
     disruptions
    0.07
     rappresent
    0.07
     _)
    0.07
     Stat
    0.07
     mascot
    0.07
    кот
    0.07
     disrupt
    0.07
     enkel
    0.07
    Activations Density 0.023%

    No Known Activations