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. 12863
    Prev
    Next
    INDEX
    Explanations

    stay

    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
     Ja
    -0.08
    elike
    -0.08
     drawbacks
    -0.08
     eignet
    -0.08
     выда
    -0.07
     அதிக
    -0.07
    Via
    -0.07
     benötigt
    -0.07
     eignen
    -0.07
     लागत
    -0.07
    POSITIVE LOGITS
     maths
    0.08
     vibrant
    0.08
     thoughtful
    0.08
    传播
    0.08
     imaginative
    0.08
    数学
    0.08
    visions
    0.08
     adventurous
    0.08
     socials
    0.08
     microbes
    0.07
    Activations Density 0.023%

    No Known Activations