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. 113885
    Prev
    Next
    INDEX
    Explanations

    random content generation

    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
    .PARAM
    -0.08
    _extent
    -0.08
     PARAM
    -0.08
     ejecución
    -0.08
    kka
    -0.08
     xmm
    -0.08
     replication
    -0.08
     sumi
    -0.08
    _scaled
    -0.07
    tev
    -0.07
    POSITIVE LOGITS
     random
    0.15
    random
    0.14
     Random
    0.14
     randomness
    0.14
    _random
    0.13
    Random
    0.13
    随机
    0.13
    =random
    0.13
    (random
    0.13
    .random
    0.13
    Activations Density 0.008%

    No Known Activations