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. 45159
    Prev
    Next
    INDEX
    Explanations

    Mesopotamia

    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
    Modify
    -0.09
    foreach
    -0.09
    encion
    -0.08
    modify
    -0.08
    confidence
    -0.08
     QModel
    -0.08
    indra
    -0.08
     sunshine
    -0.08
     summertime
    -0.07
    年前
    -0.07
    POSITIVE LOGITS
     ASIC
    0.09
     tablets
    0.08
    <\/
    0.08
     Babylon
    0.08
     Tablets
    0.08
     ancient
    0.08
    �
    0.08
     Gia
    0.08
     civilizations
    0.08
     Ancient
    0.08
    Activations Density 0.015%

    No Known Activations