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. 58827
    Prev
    Next
    INDEX
    Explanations

    property

    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
     �
    -0.09
     federal
    -0.08
     Kumar
    -0.08
    igers
    -0.08
     заявку
    -0.07
     mån
    -0.07
    igen
    -0.07
    lah
    -0.07
    waren
    -0.07
    िली
    -0.07
    POSITIVE LOGITS
     whereby
    0.10
    产权
    0.08
    规律
    0.08
     nicely
    0.08
     geeks
    0.08
     hv
    0.08
     regarding
    0.07
     Brewer
    0.07
     symmetrical
    0.07
    别人
    0.07
    Activations Density 0.013%

    No Known Activations