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. 52896
    Prev
    Next
    INDEX
    Explanations

    people

    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
     nay
    -0.08
     heim
    -0.07
    毫米
    -0.07
     midnight
    -0.07
     feet
    -0.07
    feet
    -0.07
     midfielder
    -0.07
     chans
    -0.07
     ears
    -0.07
     Shock
    -0.07
    POSITIVE LOGITS
     소개
    0.09
     cursus
    0.08
     사람
    0.08
    들과
    0.08
    들을
    0.08
    소개
    0.08
     버
    0.08
    افحة
    0.08
     people's
    0.07
     profil
    0.07
    Activations Density 0.139%

    No Known Activations