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. 8588
    Prev
    Next
    INDEX
    Explanations

    oler

    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
    ged
    -0.07
    ovement
    -0.07
    .effect
    -0.07
     전
    -0.07
     sucking
    -0.07
    .environment
    -0.07
     advocating
    -0.07
    lange
    -0.07
    .authentication
    -0.07
    랩
    -0.07
    POSITIVE LOGITS
     తెలిస
    0.07
     contraire
    0.07
     postgraduate
    0.07
     క్ల
    0.07
    леж
    0.07
     hakan
    0.07
     способ
    0.07
    ાપ્ત
    0.07
    ირება
    0.07
     Jornada
    0.07
    Activations Density 0.258%

    No Known Activations