Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 106185
    Prev
    Next
    INDEX
    Explanations

    code and math

    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
    סום
    -0.08
    beg
    -0.08
     явля
    -0.08
     если
    -0.08
    	act
    -0.08
     статья
    -0.08
    uentas
    -0.07
     в
    -0.07
    账
    -0.07
     ст
    -0.07
    POSITIVE LOGITS
     clinically
    0.07
     معها
    0.07
    ::.
    0.07
    DG
    0.07
    -cloud
    0.07
     Telekom
    0.07
    Cloud
    0.07
    DE
    0.07
    _cloud
    0.07
     psychologist
    0.07
    Activations Density 0.000%

    No Known Activations