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. 76176
    Prev
    Next
    INDEX
    Explanations

    justification

    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
     вяз
    -0.08
     Pricing
    -0.08
     טיפול
    -0.08
     dropping
    -0.08
     баб
    -0.08
     nghiệp
    -0.08
    рош
    -0.07
     Stripe
    -0.07
     бах
    -0.07
    legacy
    -0.07
    POSITIVE LOGITS
     epistem
    0.10
     conviction
    0.08
    加载
    0.08
     certainty
    0.08
    certainty
    0.08
     doğr
    0.08
     pust
    0.08
    期期
    0.08
     عقل
    0.08
     beliefs
    0.08
    Activations Density 0.007%

    No Known Activations