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. 113785
    Prev
    Next
    INDEX
    Explanations

    lend

    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
     сво
    -0.08
    addons
    -0.07
    ld
    -0.07
     अग
    -0.07
    nus
    -0.07
     Jays
    -0.07
    -0.07
    ళ్ల
    -0.07
     진
    -0.07
    tex
    -0.07
    POSITIVE LOGITS
    받
    0.08
    出去
    0.08
     mens
    0.08
     kepada
    0.07
    anas
    0.07
     Kate
    0.07
    ומ
    0.07
    义
    0.07
    וגע
    0.07
     mobil
    0.07
    Activations Density 0.004%

    No Known Activations