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. 103160
    Prev
    Next
    INDEX
    Explanations

    maximum

    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
    However
    -0.07
    breadcrumbs
    -0.07
     Scheme
    -0.07
     خطوة
    -0.07
     surprisingly
    -0.07
     provision
    -0.07
    Scheme
    -0.07
    .backends
    -0.07
     frontend
    -0.07
    Partial
    -0.07
    POSITIVE LOGITS
    峰
    0.12
     maxima
    0.12
     extrema
    0.11
     maximizing
    0.11
     peak
    0.11
     pinnacle
    0.10
     �
    0.10
     maximize
    0.10
     Maxim
    0.10
     maxim
    0.10
    Activations Density 0.024%

    No Known Activations