© 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. 75411
    Prev
    Next
    INDEX
    Explanations

    850

    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
     cutting
    -0.08
     bol
    -0.08
     Bol
    -0.07
     domain
    -0.07
    bol
    -0.07
    !--
    -0.07
     KS
    -0.07
     anthrop
    -0.07
     generated
    -0.07
    -0.07
    POSITIVE LOGITS
     awake
    0.09
     confort
    0.08
    awake
    0.08
     Proposal
    0.08
     Commonwealth
    0.08
     Blog
    0.08
    essian
    0.08
    Paypal
    0.07
     Zwischen
    0.07
     Codec
    0.07
    Activations Density 0.009%
    No Known Activations