© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29508
    Prev
    Next
    INDEX
    Explanations

    Argumentative/analytical writing

    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
    Jake
    -0.07
     revital
    -0.07
     김
    -0.07
    manın
    -0.07
     gł
    -0.07
     함께
    -0.07
    ●
    -0.07
     positioned
    -0.07
     원
    -0.07
    ాతో
    -0.07
    POSITIVE LOGITS
     ape
    0.09
     Mathematical
    0.09
     ought
    0.09
     consequent
    0.08
    webkit
    0.08
     neoliberal
    0.08
     sui
    0.08
    数学
    0.08
    。当然
    0.08
     mathematical
    0.08
    Activations Density 0.797%

    No Known Activations