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. 43276
    Prev
    Next
    INDEX
    Explanations

    sways

    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
    editor
    -0.08
    -ion
    -0.08
     unanimously
    -0.07
     commissioner
    -0.07
    сел
    -0.07
    委员会
    -0.07
    pecific
    -0.07
     आयोज
    -0.07
     conoc
    -0.07
    imp
    -0.07
    POSITIVE LOGITS
     Fahrt
    0.09
     atrás
    0.09
     sitzt
    0.08
     stroll
    0.08
     alami
    0.08
     ^=
    0.08
    杏
    0.08
    raut
    0.08
    Cabe
    0.08
    DIT
    0.08
    Activations Density 0.004%

    No Known Activations