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. 103868
    Prev
    Next
    INDEX
    Explanations

    Asking clarifying questions

    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
     schließlich
    -0.08
     നമ്മുടെ
    -0.08
     Sexual
    -0.07
     pozost
    -0.07
     Dein
    -0.07
    私
    -0.07
    יינו
    -0.07
    udience
    -0.07
     المكان
    -0.07
     આપણ
    -0.07
    POSITIVE LOGITS
     хотите
    0.10
     souhaitez
    0.10
     도움이
    0.09
     avez
    0.08
     deseja
    0.08
    _LITERAL
    0.08
     চান
    0.08
     möchten
    0.08
     voulez
    0.08
     चाहते
    0.08
    Activations Density 0.024%

    No Known Activations