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. 46192
    Prev
    Next
    INDEX
    Explanations

    increase

    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
    109
    -0.08
    204
    -0.08
    326
    -0.08
    205
    -0.08
    .general
    -0.07
    -0.07
     cust
    -0.07
    104
    -0.07
    Ar
    -0.07
    선
    -0.07
    POSITIVE LOGITS
    百分点
    0.09
    /change
    0.09
    (Change
    0.09
     cambiado
    0.09
     વધારો
    0.09
     hausse
    0.09
     증가
    0.09
     causada
    0.09
     brought
    0.09
     caused
    0.09
    Activations Density 0.035%

    No Known Activations