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. 103850
    Prev
    Next
    INDEX
    Explanations

    memories

    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
     ආ
    -0.08
    .soap
    -0.08
    ARM
    -0.08
     구조
    -0.08
     Rolex
    -0.08
    _ARM
    -0.08
     XHTML
    -0.08
    udis
    -0.08
    倫理
    -0.08
     Bedien
    -0.08
    POSITIVE LOGITS
     funny
    0.11
     shared
    0.11
     gemeinsamen
    0.11
     gemeinsame
    0.10
     memorabilia
    0.09
     history
    0.09
     humorous
    0.09
     القديم
    0.09
    shared
    0.09
     accumulated
    0.09
    Activations Density 0.023%

    No Known Activations