© 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. 99254
    Prev
    Next
    INDEX
    Explanations

    private insurance

    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
    robot
    -0.09
    anit
    -0.08
    于
    -0.08
     Musical
    -0.08
     manufact
    -0.08
     cén
    -0.08
     immin
    -0.08
     We're
    -0.08
    Robot
    -0.08
    -video
    -0.08
    POSITIVE LOGITS
     private
    0.13
     निजी
    0.12
     privately
    0.12
    私人
    0.12
     സ്വകാര്യ
    0.12
     individualized
    0.11
     ખાન
    0.11
     privata
    0.10
     privadas
    0.10
    _private
    0.10
    Activations Density 0.027%

    No Known Activations