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. 53904
    Prev
    Next
    INDEX
    Explanations

    teenagers

    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
     Shea
    -0.08
     сти
    -0.07
     regard
    -0.07
     Mam
    -0.07
     mam
    -0.07
    257
    -0.07
    Sc
    -0.07
     Ita
    -0.07
    GM
    -0.07
     regards
    -0.07
    POSITIVE LOGITS
    0.08
     extending
    0.08
    0.08
    اريع
    0.07
     بقي
    0.07
     aks
    0.07
    ACC
    0.07
     HQ
    0.07
     hanger
    0.07
     बर्ष
    0.07
    Activations Density 1.529%

    No Known Activations