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. 114126
    Prev
    Next
    INDEX
    Explanations

    .

    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
    AB
    -0.08
     form
    -0.07
    -0.07
    _ne
    -0.07
    nej
    -0.07
    .Hash
    -0.07
     বের
    -0.07
     Henri
    -0.07
    :</
    -0.07
    邻
    -0.07
    POSITIVE LOGITS
     Eles
    0.09
     titular
    0.08
     directives
    0.08
     आदेश
    0.08
    Lite
    0.08
     vegetal
    0.08
     pediu
    0.08
    ITOR
    0.08
     निभ
    0.08
     الأشياء
    0.08
    Activations Density 0.008%

    No Known Activations