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. 90109
    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
    smöglichkeiten
    -0.08
     Ike
    -0.08
     Jah
    -0.07
     Biz
    -0.07
     sick
    -0.07
     Abroad
    -0.07
     Aber
    -0.07
    iris
    -0.07
     Sauer
    -0.07
    -0.07
    POSITIVE LOGITS
    Company
    0.09
     stated
    0.09
     funding
    0.09
    Funding
    0.08
     family's
    0.08
     Company's
    0.08
     Funding
    0.08
     organization's
    0.08
     fundraising
    0.08
    քան
    0.08
    Activations Density 0.007%

    No Known Activations