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. 98843
    Prev
    Next
    INDEX
    Explanations

    who

    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
    (){
    ↵
    -0.09
    _CONFIGURATION
    -0.08
    '){
    ↵
    -0.08
    {
    ↵
    -0.08
    :function
    -0.08
    .Ma
    -0.08
     lòng
    -0.08
    .Component
    -0.08
     сердце
    -0.07
    -0.07
    POSITIVE LOGITS
     Split
    0.08
     split
    0.08
     Guaranteed
    0.08
     Angehör
    0.07
     naro
    0.07
     osobe
    0.07
     Gav
    0.07
     люб
    0.07
     очевид
    0.07
     £
    0.07
    Activations Density 0.001%

    No Known Activations