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. 90202
    Prev
    Next
    INDEX
    Explanations

    lipstick

    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
     pitched
    -0.08
    Termination
    -0.08
    GA
    -0.07
     올해
    -0.07
    termination
    -0.07
    465
    -0.07
    हाल
    -0.07
    imation
    -0.07
     aeg
    -0.07
     GA
    -0.07
    POSITIVE LOGITS
    κλο
    0.09
     lipstick
    0.08
    �
    0.08
     खो
    0.08
     antique
    0.08
    工具
    0.08
     قيمة
    0.08
     địa
    0.08
     eyeliner
    0.08
     cherry
    0.08
    Activations Density 0.001%

    No Known Activations