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. 9102
    Prev
    Next
    INDEX
    Explanations

    Responding to a prompt

    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
    chel
    -0.09
    _ele
    -0.08
    .margin
    -0.08
     étions
    -0.08
    ांची
    -0.08
    _margin
    -0.08
    _ALIGN
    -0.07
    .en
    -0.07
    ח
    -0.07
    ynet
    -0.07
    POSITIVE LOGITS
    vertices
    0.08
     ο
    0.08
    -ts
    0.08
     aand
    0.07
    vary
    0.07
    ':'
    0.07
    symbols
    0.07
     Baud
    0.07
     Qgs
    0.07
     Locale
    0.07
    Activations Density 0.194%

    No Known Activations