© 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. 64960
    Prev
    Next
    INDEX
    Explanations

    derivatives and subgradients

    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
     dilution
    -0.08
    research
    -0.08
    -0.07
    Invest
    -0.07
    (Logger
    -0.07
    .put
    -0.07
     bait
    -0.07
    (World
    -0.07
     тщательно
    -0.07
     resonates
    -0.07
    POSITIVE LOGITS
    裸
    0.09
     symbolic
    0.09
    âteaux
    0.09
    怒
    0.09
     shock
    0.08
    蒲
    0.08
     tantr
    0.08
     pierced
    0.08
     discontinu
    0.08
     carnegie
    0.08
    Activations Density 0.013%
    No Known Activations