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. 117484
    Prev
    Next
    INDEX
    Explanations

    for

    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
    েমন
    -0.08
    风
    -0.08
    তম
    -0.08
     انف
    -0.08
    账号
    -0.07
     equipment
    -0.07
     sendiri
    -0.07
     DD
    -0.07
     decree
    -0.07
    _pet
    -0.07
    POSITIVE LOGITS
     sucesso
    0.08
     कही
    0.08
     homelessness
    0.08
     falsely
    0.08
    Spam
    0.08
    crire
    0.08
     innocence
    0.07
     रिश्त
    0.07
     accomplish
    0.07
     clo
    0.07
    Activations Density 0.006%

    No Known Activations