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. 11785
    Prev
    Next
    INDEX
    Explanations

    race

    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
     grind
    -0.09
    तम
    -0.09
     parab
    -0.09
     Provided
    -0.08
     Pane
    -0.08
     waist
    -0.08
    Provided
    -0.08
    ర్త
    -0.08
     spine
    -0.07
     aka
    -0.07
    POSITIVE LOGITS
     vil
    0.10
     Eun
    0.09
     conspiracy
    0.09
    -conscious
    0.08
     ikke
    0.08
     neutrality
    0.08
     cons
    0.08
    -neutral
    0.08
     kun
    0.08
     Eleven
    0.08
    Activations Density 0.009%

    No Known Activations