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. 23879
    Prev
    Next
    INDEX
    Explanations

    bus stops

    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
    scope
    -0.09
     subconscious
    -0.08
     masque
    -0.08
     scope
    -0.08
     scopes
    -0.08
    Scope
    -0.08
    otropic
    -0.08
    _SCOPE
    -0.08
     jedes
    -0.08
     masked
    -0.08
    POSITIVE LOGITS
    站
    0.11
     At
    0.08
    先锋
    0.08
     ವಿಮ
    0.08
    .Wait
    0.08
     ಬಳಿ
    0.08
     останов
    0.08
     speeches
    0.07
     Wirk
    0.07
     waiting
    0.07
    Activations Density 0.012%

    No Known Activations