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. 106050
    Prev
    Next
    INDEX
    Explanations

    Listener

    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
     волосы
    -0.08
     tree
    -0.08
    Trees
    -0.08
    лось
    -0.08
     х
    -0.08
    .Tree
    -0.08
     ет
    -0.07
     cabello
    -0.07
     trees
    -0.07
     въ
    -0.07
    POSITIVE LOGITS
    (timeout
    0.07
    色情
    0.07
    _ssl
    0.07
    Ssl
    0.07
     Austral
    0.07
     Paran
    0.07
    (set
    0.07
     Parmesan
    0.07
     comprendre
    0.07
    Pile
    0.07
    Activations Density 0.000%

    No Known Activations