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. 113782
    Prev
    Next
    INDEX
    Explanations

    head

    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
     Olsen
    -0.09
    _people
    -0.08
    People
    -0.07
    Iterator
    -0.07
    öszön
    -0.07
     everybody
    -0.07
    Firstname
    -0.07
    solar
    -0.07
    लोक
    -0.07
     solar
    -0.07
    POSITIVE LOGITS
     Differ
    0.09
     Lem
    0.08
    axaca
    0.08
     ورو
    0.08
    .JSONException
    0.08
     найд
    0.08
     ځ
    0.08
     блюда
    0.07
     Definitions
    0.07
     дог
    0.07
    Activations Density 0.001%

    No Known Activations