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. 102779
    Prev
    Next
    INDEX
    Explanations

    Settings

    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
    linux
    -0.08
    rails
    -0.07
    onner
    -0.07
    .netbeans
    -0.07
    ateur
    -0.07
     rampant
    -0.07
    Identifiers
    -0.07
    Identifier
    -0.07
    WARNING
    -0.07
    Diagn
    -0.07
    POSITIVE LOGITS
     tourism
    0.09
     पर्यटन
    0.08
    ayaasha
    0.08
     verso
    0.08
     baggage
    0.08
     tane
    0.08
     masalah
    0.08
    व
    0.07
     Tokio
    0.07
     pravil
    0.07
    Activations Density 0.002%

    No Known Activations