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. 113931
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    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
    leden
    -0.09
    elijkse
    -0.09
    ämme
    -0.08
    boro
    -0.08
     فعالیت
    -0.08
    ubscriber
    -0.08
     Branche
    -0.08
    াটা
    -0.07
    ells
    -0.07
    ovy
    -0.07
    POSITIVE LOGITS
     cent
    0.08
     spelled
    0.08
     ciment
    0.07
    基本
    0.07
     impress
    0.07
     defeating
    0.07
    Ñ
    0.07
     ce
    0.07
    _TOO
    0.07
     quilting
    0.07
    Activations Density 0.048%

    No Known Activations