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. 74571
    Prev
    Next
    INDEX
    Explanations

    match

    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
    formations
    -0.08
    stanbul
    -0.08
    part
    -0.07
    lera
    -0.07
    paint
    -0.07
    griff
    -0.07
    -0.07
     Sem
    -0.07
    enom
    -0.07
    psilon
    -0.07
    POSITIVE LOGITS
     funds
    0.11
     enthousiast
    0.10
     निध
    0.09
     Funds
    0.09
     donations
    0.08
     الأموال
    0.08
     venga
    0.08
     veng
    0.08
     spons
    0.08
     Yours
    0.08
    Activations Density 0.002%

    No Known Activations