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. 101632
    Prev
    Next
    INDEX
    Explanations

    positive sentiment

    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
    ਣਾ
    -0.08
    ząc
    -0.08
     abras
    -0.08
    actical
    -0.08
    ਵੀ
    -0.07
     적극
    -0.07
    ieres
    -0.07
     específicamente
    -0.07
    ikeun
    -0.07
     Core
    -0.07
    POSITIVE LOGITS
    ليف
    0.08
     lineup
    0.07
     */
    0.07
    0.07
     reino
    0.07
     premise
    0.07
     shed
    0.07
     atrop
    0.07
     Galway
    0.07
     الدا
    0.07
    Activations Density 0.219%

    No Known Activations