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. 119390
    Prev
    Next
    INDEX
    Explanations

    Contact information

    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
    .samples
    -0.08
    .pixel
    -0.07
    Wh
    -0.07
    .cpp
    -0.07
    .Ar
    -0.07
    .utils
    -0.07
     घंट
    -0.07
    .raise
    -0.07
    .fail
    -0.07
     నెల
    -0.07
    POSITIVE LOGITS
     Dutch
    0.13
     Nederlandse
    0.12
     Netherlands
    0.12
     Nederlands
    0.12
    Belg
    0.11
    Dutch
    0.11
     gezellig
    0.10
     Flem
    0.10
     Amsterdam
    0.10
     dry
    0.10
    Activations Density 0.083%

    No Known Activations