© 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. 117
    Prev
    Next
    INDEX
    Explanations

    paralympics

    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
     tmpl
    -0.09
     Montessori
    -0.09
     Angeb
    -0.08
     Vacancy
    -0.08
    454
    -0.08
    hire
    -0.08
     intimid
    -0.08
    reda
    -0.08
    Hiring
    -0.08
    etlen
    -0.08
    POSITIVE LOGITS
     describes
    0.08
     contains
    0.07
     enters
    0.07
     вик
    0.07
     criter
    0.07
     गौर
    0.07
     elevation
    0.07
     Francisco
    0.07
     member
    0.07
     submitted
    0.07
    Activations Density 0.003%

    No Known Activations