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. 120109
    Prev
    Next
    INDEX
    Explanations

    looking

    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
     porém
    -0.08
     vertr
    -0.08
    -browser
    -0.08
     vél
    -0.08
     HBO
    -0.07
     verletzt
    -0.07
    worked
    -0.07
     sodass
    -0.07
    -comments
    -0.07
    (iv
    -0.07
    POSITIVE LOGITS
    ்ல
    0.08
    ((_
    0.07
     congress
    0.07
    �
    0.07
    _byte
    0.07
    othy
    0.07
     lately
    0.07
     Cyprus
    0.07
    leti
    0.07
     Enumerable
    0.07
    Activations Density 0.045%

    No Known Activations