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. 9169
    Prev
    Next
    INDEX
    Explanations

    install

    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
     duplication
    -0.08
    branche
    -0.08
     bounded
    -0.08
     branching
    -0.08
    гал
    -0.08
    सँग
    -0.08
     rằng
    -0.07
    -0.07
     broccoli
    -0.07
     dup
    -0.07
    POSITIVE LOGITS
    闲
    0.08
     impression
    0.08
     elettron
    0.08
     shut
    0.08
     remainder
    0.08
    {}_
    0.07
    838
    0.07
    rem
    0.07
     الرك
    0.07
     swimsuit
    0.07
    Activations Density 0.001%

    No Known Activations