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. 55819
    Prev
    Next
    INDEX
    Explanations

    dinner

    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
     CT
    -0.08
    @Controller
    -0.07
    -lined
    -0.07
     gild
    -0.07
     él
    -0.07
    nest
    -0.07
     nesting
    -0.07
    ций
    -0.07
     அல
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     dinner
    0.10
    /night
    0.09
     dinners
    0.08
     Keb
    0.08
     trif
    0.08
     tonight
    0.08
     Hist
    0.08
    (movie
    0.08
    rying
    0.08
     pleas
    0.08
    Activations Density 0.006%

    No Known Activations