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. 112684
    Prev
    Next
    INDEX
    Explanations

    Hex color codes

    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
     hub
    -0.08
     recruiter
    -0.07
    OH
    -0.07
    Expose
    -0.07
     locomotive
    -0.07
    대
    -0.07
     Hub
    -0.07
     alap
    -0.07
     Nexus
    -0.07
     scratched
    -0.07
    POSITIVE LOGITS
     anu
    0.08
     sky
    0.08
     Dancing
    0.08
    /an
    0.07
    /he
    0.07
     Süd
    0.07
     svak
    0.07
     ngagaduhan
    0.07
     volg
    0.07
     gần
    0.07
    Activations Density 0.007%

    No Known Activations