© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47948
    Prev
    Next
    INDEX
    Explanations

    Loss calculation

    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
     governments
    -0.08
     kicker
    -0.08
     arf
    -0.07
    iptir
    -0.07
     apt
    -0.07
     enterprise
    -0.07
    itsa
    -0.07
     strike
    -0.07
     rational
    -0.07
    δί
    -0.07
    POSITIVE LOGITS
    /design
    0.08
    flow
    0.08
     రచ
    0.08
    niet
    0.07
    (flow
    0.07
     �
    0.07
     metabolism
    0.07
     Loss
    0.07
    /job
    0.07
     postings
    0.07
    Activations Density 0.003%

    No Known Activations