© 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. 19-RESID-POST-AA
    11. 102899
    Prev
    Next
    INDEX
    Explanations

    people involved

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     naszego
    -0.08
     została
    -0.08
     vårt
    -0.08
     Instructor
    -0.08
    We
    -0.08
     हमारा
    -0.07
     friend's
    -0.07
     USER
    -0.07
    σουμε
    -0.07
     Nous
    -0.07
    POSITIVE LOGITS
     players
    0.24
     athletes
    0.24
     participants
    0.24
     individuals
    0.23
     students
    0.23
     patients
    0.23
     افراد
    0.21
     contestants
    0.21
     inmates
    0.21
     employees
    0.20
    Activations Density 0.201%

    No Known Activations