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. 87954
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     kalk
    -0.08
     dü
    -0.08
     Hör
    -0.07
     består
    -0.07
    вания
    -0.07
     uniforme
    -0.07
     fatta
    -0.07
     tü
    -0.07
     Hanna
    -0.07
     каль
    -0.07
    POSITIVE LOGITS
    -containing
    0.10
     অন্ত
    0.09
     ছাড়া
    0.09
     Alone
    0.08
     সঙ্গে
    0.08
     Inclusion
    0.08
     alone
    0.08
    ურთ
    0.08
     সাথে
    0.07
     વગર
    0.07
    Activations Density 0.021%

    No Known Activations