Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11704
    Prev
    Next
    INDEX
    Explanations

    code/formulas

    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
    ం
    -0.08
     Martini
    -0.07
    George
    -0.07
    לו
    -0.07
     however
    -0.07
     nag
    -0.07
    ೆಯ
    -0.07
     Lazar
    -0.07
    CG
    -0.07
    ום
    -0.07
    POSITIVE LOGITS
     എല്ലാ
    0.09
    mmat
    0.09
     Layer
    0.08
     എല്ല
    0.08
     слоя
    0.08
    icur
    0.08
     ട
    0.08
    /Add
    0.08
    cratch
    0.08
    ��
    0.08
    Activations Density 0.041%

    No Known Activations