© 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. 23-RESID-POST-AA
    11. 48646
    Prev
    Next
    INDEX
    Explanations

    Numbers around 360

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rdf
    -0.09
     paran
    -0.09
     Disease
    -0.09
     Stacy
    -0.09
     Stan
    -0.09
     Disorder
    -0.09
     Parsons
    -0.09
    (stmt
    -0.09
     синд
    -0.08
     stmt
    -0.08
    POSITIVE LOGITS
    360
    0.38
    361
    0.23
    359
    0.22
    363
    0.19
    362
    0.18
    358
    0.17
    364
    0.15
     magnet
    0.14
    36
    0.13
    356
    0.13
    Activations Density 0.044%

    No Known Activations