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. 53210
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     Montage
    -0.09
     Romero
    -0.08
     montage
    -0.08
    -0.08
     penalty
    -0.07
     dripping
    -0.07
     crest
    -0.07
     chiến
    -0.07
     vraiment
    -0.07
     Jad
    -0.07
    POSITIVE LOGITS
     ок
    0.09
     literally
    0.08
    Please
    0.08
    Approximately
    0.08
     requiring
    0.08
     �
    0.08
    (find
    0.08
     взять
    0.08
    (bus
    0.07
     trovare
    0.07
    Activations Density 0.022%

    No Known Activations