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. 120204
    Prev
    Next
    INDEX
    Explanations

    discharge

    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
     élevée
    -0.08
     relo
    -0.08
     grids
    -0.07
     giga
    -0.07
     investissement
    -0.07
     コピー
    -0.07
    .Radio
    -0.07
     투자
    -0.07
     élev
    -0.07
     essay
    -0.07
    POSITIVE LOGITS
    -filled
    0.08
     ಬರುತ್ತ
    0.08
     ric
    0.08
     saliva
    0.08
     devam
    0.08
    @login
    0.07
    kommt
    0.07
     rất
    0.07
     stammt
    0.07
    تى
    0.07
    Activations Density 0.007%

    No Known Activations