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. 112122
    Prev
    Next
    INDEX
    Explanations

    database tables and ids

    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
     locals
    -0.09
     &=
    -0.08
    _ALIGNMENT
    -0.08
     smear
    -0.08
     worden
    -0.07
     الوس
    -0.07
    ettel
    -0.07
     Slight
    -0.07
     الأمر
    -0.07
     Fb
    -0.07
    POSITIVE LOGITS
    主
    0.08
    Pric
    0.08
     wajib
    0.08
     主
    0.07
     dong
    0.07
     मुख्य
    0.07
    _flat
    0.07
    dong
    0.07
     터
    0.07
    ylie
    0.07
    Activations Density 0.006%

    No Known Activations