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. 43675
    Prev
    Next
    INDEX
    Explanations

    ators

    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
    _ptr
    -0.09
     NSIndex
    -0.08
    Mash
    -0.07
    Ptr
    -0.07
    否
    -0.07
    ron
    -0.07
     handlebars
    -0.07
    ndag
    -0.07
     observed
    -0.07
    PTR
    -0.07
    POSITIVE LOGITS
     sufficient
    0.08
     compreh
    0.08
     tatau
    0.08
     diligently
    0.08
    SEARCH
    0.08
     саны
    0.08
     충분
    0.08
    759
    0.08
     cento
    0.08
     kūpono
    0.07
    Activations Density 0.002%

    No Known Activations