Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60671
    Prev
    Next
    INDEX
    Explanations

    DES encryption

    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
     butik
    -0.09
     Boutique
    -0.08
    iksaan
    -0.08
     boutique
    -0.08
     hãng
    -0.08
    ísimo
    -0.08
     Ramp
    -0.08
     حدوث
    -0.08
    ャン
    -0.08
     сапраў
    -0.07
    POSITIVE LOGITS
     Einführung
    0.08
    INTRO
    0.08
     Grenze
    0.08
    Famil
    0.08
    input
    0.08
     endpoint
    0.08
    manifest
    0.08
    र्ल
    0.08
    zm
    0.08
    ?!
    0.08
    Activations Density 0.000%

    No Known Activations