© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1335
    Prev
    Next
    INDEX
    Explanations

    friends/cousins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acre
    -0.08
    эгдэх
    -0.07
     Christchurch
    -0.07
     Composition
    -0.07
     붙
    -0.07
     composition
    -0.07
    agreement
    -0.07
    Bib
    -0.07
    μι
    -0.07
     guests
    -0.07
    POSITIVE LOGITS
     {@
    0.08
    ouli
    0.08
     {{
    0.08
    .ns
    0.07
     *_
    0.07
     -->
    0.07
     {_
    0.07
    powered
    0.07
     peuples
    0.07
    ->_
    0.07
    Activations Density 0.048%

    No Known Activations