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. 9262
    Prev
    Next
    INDEX
    Explanations

    plane engine failure

    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
     anime
    -0.08
     fetish
    -0.08
     mees
    -0.08
    ას
    -0.08
     reproduct
    -0.08
     uruh
    -0.08
    Anime
    -0.08
    .anim
    -0.07
     kiosk
    -0.07
     roc
    -0.07
    POSITIVE LOGITS
     integrity
    0.10
     Integrity
    0.08
    干部
    0.08
     flange
    0.08
    Integrity
    0.08
    okom
    0.07
    ormal
    0.07
    trim
    0.07
     hatch
    0.07
    flammation
    0.07
    Activations Density 0.013%

    No Known Activations