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. 45023
    Prev
    Next
    INDEX
    Explanations

    _

    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
    kosten
    -0.09
     Oral
    -0.08
     उम
    -0.07
    atinum
    -0.07
     prescription
    -0.07
     flea
    -0.07
    -column
    -0.07
    oral
    -0.07
     dure
    -0.07
    үп
    -0.07
    POSITIVE LOGITS
     ....
    0.08
    Pa
    0.08
     IOC
    0.08
     jed
    0.08
     Pa
    0.07
     �
    0.07
    å
    0.07
    Tray
    0.07
     ______
    0.07
     IDs
    0.07
    Activations Density 0.002%

    No Known Activations