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. 58129
    Prev
    Next
    INDEX
    Explanations

    careers

    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
     հիշ
    -0.09
     KEY
    -0.08
     Ք
    -0.08
    .KEY
    -0.08
     frein
    -0.08
     гэтага
    -0.08
     achat
    -0.08
     ട
    -0.08
     Кит
    -0.08
     انتاج
    -0.08
    POSITIVE LOGITS
     personally
    0.09
     personal
    0.08
     personnelle
    0.08
     personales
    0.08
     Personal
    0.08
    Own
    0.08
    Personal
    0.07
     propria
    0.07
    /dist
    0.07
     pessoais
    0.07
    Activations Density 0.213%

    No Known Activations