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. 30183
    Prev
    Next
    INDEX
    Explanations

    capacitor

    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
     extent
    -0.08
    extent
    -0.08
     Sons
    -0.08
    loc
    -0.08
     Lus
    -0.07
    .loc
    -0.07
     masculine
    -0.07
    ેખ
    -0.07
    ণ
    -0.07
    িকার
    -0.07
    POSITIVE LOGITS
     verlangt
    0.08
     chim
    0.08
     dojo
    0.08
    그래
    0.08
     stereo
    0.08
     chir
    0.08
     υ
    0.07
     चालक
    0.07
     hardness
    0.07
     conditioners
    0.07
    Activations Density 0.002%

    No Known Activations